Alvaro Velasquez

Mingju Liu, Jiaqi Yin, Alvaro Velasquez et al.

This paper presents a hybrid CPU-GPU framework for solving combinatorial scheduling problems formulated as Integer Linear Programming (ILP). While scheduling underpins many optimization tasks in computing systems, solving these problems optimally at scale remains a long-standing challenge due to their NP-hard nature. We introduce a novel approach that combines differentiable optimization with classical ILP solving. Specifically, we utilize differentiable presolving to rapidly generate high-quality partial solutions, which serve as warm-starts for commercial ILP solvers (CPLEX, Gurobi) and rising open-source solver HiGHS. This method enables significantly improved early pruning compared to state-of-the-art standalone solvers. Empirical results across industry-scale benchmarks demonstrate up to a $10\times$ performance gain over baselines, narrowing the optimality gap to $<0.1\%$. This work represents the first demonstration of utilizing differentiable optimization to initialize exact ILP solvers for combinatorial scheduling, opening new opportunities to integrate machine learning infrastructure with classical exact optimization methods across broader domains.

Abhinav Rajvanshi, Karan Sikka, Xiao Lin et al.

Semantic reasoning and dynamic planning capabilities are crucial for an autonomous agent to perform complex navigation tasks in unknown environments. It requires a large amount of common-sense knowledge, that humans possess, to succeed in these tasks. We present SayNav, a new approach that leverages human knowledge from Large Language Models (LLMs) for efficient generalization to complex navigation tasks in unknown large-scale environments. SayNav uses a novel grounding mechanism, that incrementally builds a 3D scene graph of the explored environment as inputs to LLMs, for generating feasible and contextually appropriate high-level plans for navigation. The LLM-generated plan is then executed by a pre-trained low-level planner, that treats each planned step as a short-distance point-goal navigation sub-task. SayNav dynamically generates step-by-step instructions during navigation and continuously refines future steps based on newly perceived information. We evaluate SayNav on multi-object navigation (MultiON) task, that requires the agent to utilize a massive amount of human knowledge to efficiently search multiple different objects in an unknown environment. We also introduce a benchmark dataset for MultiON task employing ProcTHOR framework that provides large photo-realistic indoor environments with variety of objects. SayNav achieves state-of-the-art results and even outperforms an oracle based baseline with strong ground-truth assumptions by more than 8% in terms of success rate, highlighting its ability to generate dynamic plans for successfully locating objects in large-scale new environments. The code, benchmark dataset and demonstration videos are accessible at https://www.sri.com/ics/computer-vision/saynav.

Wenkai Tan, Justus Renkhoff, Alvaro Velasquez et al.

Deep Learning (DL) and Deep Neural Networks (DNNs) are widely used in various domains. However, adversarial attacks can easily mislead a neural network and lead to wrong decisions. Defense mechanisms are highly preferred in safety-critical applications. In this paper, firstly, we use the gradient class activation map (GradCAM) to analyze the behavior deviation of the VGG-16 network when its inputs are mixed with adversarial perturbation or Gaussian noise. In particular, our method can locate vulnerable layers that are sensitive to adversarial perturbation and Gaussian noise. We also show that the behavior deviation of vulnerable layers can be used to detect adversarial examples. Secondly, we propose a novel NoiseCAM algorithm that integrates information from globally and pixel-level weighted class activation maps. Our algorithm is susceptible to adversarial perturbations and will not respond to Gaussian random noise mixed in the inputs. Third, we compare detecting adversarial examples using both behavior deviation and NoiseCAM, and we show that NoiseCAM outperforms behavior deviation modeling in its overall performance. Our work could provide a useful tool to defend against certain adversarial attacks on deep neural networks.

Justus Renkhoff, Wenkai Tan, Alvaro Velasquez et al.

Deep Learning (DL) is being applied in various domains, especially in safety-critical applications such as autonomous driving. Consequently, it is of great significance to ensure the robustness of these methods and thus counteract uncertain behaviors caused by adversarial attacks. In this paper, we use gradient heatmaps to analyze the response characteristics of the VGG-16 model when the input images are mixed with adversarial noise and statistically similar Gaussian random noise. In particular, we compare the network response layer by layer to determine where errors occurred. Several interesting findings are derived. First, compared to Gaussian random noise, intentionally generated adversarial noise causes severe behavior deviation by distracting the area of concentration in the networks. Second, in many cases, adversarial examples only need to compromise a few intermediate blocks to mislead the final decision. Third, our experiments revealed that specific blocks are more vulnerable and easier to exploit by adversarial examples. Finally, we demonstrate that the layers $Block4\_conv1$ and $Block5\_cov1$ of the VGG-16 model are more susceptible to adversarial attacks. Our work could provide valuable insights into developing more reliable Deep Neural Network (DNN) models.

Lijing Zhu, Qizhen Lan, Alvaro Velasquez et al.

Detecting human-object interactions (HOIs) is an intricate challenge in the field of computer vision. Existing methods for HOI detection heavily rely on appearance-based features, but these may not fully capture all the essential characteristics necessary for accurate detection. To overcome these challenges, we propose an innovative graph-based approach called TMGHOI (Translational Model for Human-Object Interaction Detection). Our method effectively captures the sentiment representation of HOIs by integrating both spatial and semantic knowledge. By representing HOIs as a graph, where the interaction components serve as nodes and their spatial relationships as edges. To extract crucial spatial and semantic information, TMGHOI employs separate spatial and semantic encoders. Subsequently, these encodings are combined to construct a knowledge graph that effectively captures the sentiment representation of HOIs. Additionally, the ability to incorporate prior knowledge enhances the understanding of interactions, further boosting detection accuracy. We conducted extensive evaluations on the widely-used HICO-DET datasets to demonstrate the effectiveness of TMGHOI. Our approach outperformed existing state-of-the-art graph-based methods by a significant margin, showcasing its potential as a superior solution for HOI detection. We are confident that TMGHOI has the potential to significantly improve the accuracy and efficiency of HOI detection. Its integration of spatial and semantic knowledge, along with its computational efficiency and practicality, makes it a valuable tool for researchers and practitioners in the computer vision community. As with any research, we acknowledge the importance of further exploration and evaluation on various datasets to establish the generalizability and robustness of our proposed method.

Yash Shukla, Wenchang Gao, Vasanth Sarathy et al.

Recent advancements in reasoning abilities of Large Language Models (LLM) has promoted their usage in problems that require high-level planning for robots and artificial agents. However, current techniques that utilize LLMs for such planning tasks make certain key assumptions such as, access to datasets that permit finetuning, meticulously engineered prompts that only provide relevant and essential information to the LLM, and most importantly, a deterministic approach to allow execution of the LLM responses either in the form of existing policies or plan operators. In this work, we propose LgTS (LLM-guided Teacher-Student learning), a novel approach that explores the planning abilities of LLMs to provide a graphical representation of the sub-goals to a reinforcement learning (RL) agent that does not have access to the transition dynamics of the environment. The RL agent uses Teacher-Student learning algorithm to learn a set of successful policies for reaching the goal state from the start state while simultaneously minimizing the number of environmental interactions. Unlike previous methods that utilize LLMs, our approach does not assume access to a propreitary or a fine-tuned LLM, nor does it require pre-trained policies that achieve the sub-goals proposed by the LLM. Through experiments on a gridworld based DoorKey domain and a search-and-rescue inspired domain, we show that generating a graphical structure of sub-goals helps in learning policies for the LLM proposed sub-goals and the Teacher-Student learning algorithm minimizes the number of environment interactions when the transition dynamics are unknown.

Yue Wang, Alvaro Velasquez, George Atia et al.

In robust Markov decision processes (MDPs), the uncertainty in the transition kernel is addressed by finding a policy that optimizes the worst-case performance over an uncertainty set of MDPs. While much of the literature has focused on discounted MDPs, robust average-reward MDPs remain largely unexplored. In this paper, we focus on robust average-reward MDPs, where the goal is to find a policy that optimizes the worst-case average reward over an uncertainty set. We first take an approach that approximates average-reward MDPs using discounted MDPs. We prove that the robust discounted value function converges to the robust average-reward as the discount factor $γ$ goes to $1$, and moreover, when $γ$ is large, any optimal policy of the robust discounted MDP is also an optimal policy of the robust average-reward. We further design a robust dynamic programming approach, and theoretically characterize its convergence to the optimum. Then, we investigate robust average-reward MDPs directly without using discounted MDPs as an intermediate step. We derive the robust Bellman equation for robust average-reward MDPs, prove that the optimal policy can be derived from its solution, and further design a robust relative value iteration algorithm that provably finds its solution, or equivalently, the optimal robust policy.

Sumit Kumar Jha, Susmit Jha, Patrick Lincoln et al.

Generative large language models (LLMs) with instruct training such as GPT-4 can follow human-provided instruction prompts and generate human-like responses to these prompts. Apart from natural language responses, they have also been found to be effective at generating formal artifacts such as code, plans, and logical specifications from natural language prompts. Despite their remarkably improved accuracy, these models are still known to produce factually incorrect or contextually inappropriate results despite their syntactic coherence - a phenomenon often referred to as hallucination. This limitation makes it difficult to use these models to synthesize formal artifacts that are used in safety-critical applications. Unlike tasks such as text summarization and question-answering, bugs in code, plan, and other formal artifacts produced by LLMs can be catastrophic. We posit that we can use the satisfiability modulo theory (SMT) solvers as deductive reasoning engines to analyze the generated solutions from the LLMs, produce counterexamples when the solutions are incorrect, and provide that feedback to the LLMs exploiting the dialog capability of instruct-trained LLMs. This interaction between inductive LLMs and deductive SMT solvers can iteratively steer the LLM to generate the correct response. In our experiments, we use planning over the domain of blocks as our synthesis task for evaluating our approach. We use GPT-4, GPT3.5 Turbo, Davinci, Curie, Babbage, and Ada as the LLMs and Z3 as the SMT solver. Our method allows the user to communicate the planning problem in natural language; even the formulation of queries to SMT solvers is automatically generated from natural language. Thus, the proposed technique can enable non-expert users to describe their problems in natural language, and the combination of LLMs and SMT solvers can produce provably correct solutions.

Kamal Acharya, Alvaro Velasquez, Houbing Herbert Song

This survey paper delves into the emerging and critical area of symbolic knowledge distillation in Large Language Models (LLMs). As LLMs like Generative Pre-trained Transformer-3 (GPT-3) and Bidirectional Encoder Representations from Transformers (BERT) continue to expand in scale and complexity, the challenge of effectively harnessing their extensive knowledge becomes paramount. This survey concentrates on the process of distilling the intricate, often implicit knowledge contained within these models into a more symbolic, explicit form. This transformation is crucial for enhancing the interpretability, efficiency, and applicability of LLMs. We categorize the existing research based on methodologies and applications, focusing on how symbolic knowledge distillation can be used to improve the transparency and functionality of smaller, more efficient Artificial Intelligence (AI) models. The survey discusses the core challenges, including maintaining the depth of knowledge in a comprehensible format, and explores the various approaches and techniques that have been developed in this field. We identify gaps in current research and potential opportunities for future advancements. This survey aims to provide a comprehensive overview of symbolic knowledge distillation in LLMs, spotlighting its significance in the progression towards more accessible and efficient AI systems.

Ismail Alkhouri, Sumit Jha, Andre Beckus et al.

Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been explored. This is particularly relevant given the broad social implications of such technologies and the fact that biologically small perturbations in the protein sequence do not generally lead to drastic changes in the protein structure. In this paper, we demonstrate that AlphaFold does not exhibit such robustness despite its high accuracy. This raises the challenge of detecting and quantifying the extent to which these predicted protein structures can be trusted. To measure the robustness of the predicted structures, we utilize (i) the root-mean-square deviation (RMSD) and (ii) the Global Distance Test (GDT) similarity measure between the predicted structure of the original sequence and the structure of its adversarially perturbed version. We prove that the problem of minimally perturbing protein sequences to fool protein folding neural networks is NP-complete. Based on the well-established BLOSUM62 sequence alignment scoring matrix, we generate adversarial protein sequences and show that the RMSD between the predicted protein structure and the structure of the original sequence are very large when the adversarial changes are bounded by (i) 20 units in the BLOSUM62 distance, and (ii) five residues (out of hundreds or thousands of residues) in the given protein sequence. In our experimental evaluation, we consider 111 COVID-19 proteins in the Universal Protein resource (UniProt), a central resource for protein data managed by the European Bioinformatics Institute, Swiss Institute of Bioinformatics, and the US Protein Information Resource. These result in an overall GDT similarity test score average of around 34%, demonstrating a substantial drop in the performance of AlphaFold.

Yash Shukla, Abhishek Kulkarni, Robert Wright et al.

Despite advances in Reinforcement Learning, many sequential decision making tasks remain prohibitively expensive and impractical to learn. Recently, approaches that automatically generate reward functions from logical task specifications have been proposed to mitigate this issue; however, they scale poorly on long-horizon tasks (i.e., tasks where the agent needs to perform a series of correct actions to reach the goal state, considering future transitions while choosing an action). Employing a curriculum (a sequence of increasingly complex tasks) further improves the learning speed of the agent by sequencing intermediate tasks suited to the learning capacity of the agent. However, generating curricula from the logical specification still remains an unsolved problem. To this end, we propose AGCL, Automaton-guided Curriculum Learning, a novel method for automatically generating curricula for the target task in the form of Directed Acyclic Graphs (DAGs). AGCL encodes the specification in the form of a deterministic finite automaton (DFA), and then uses the DFA along with the Object-Oriented MDP (OOMDP) representation to generate a curriculum as a DAG, where the vertices correspond to tasks, and edges correspond to the direction of knowledge transfer. Experiments in gridworld and physics-based simulated robotics domains show that the curricula produced by AGCL achieve improved time-to-threshold performance on a complex sequential decision-making problem relative to state-of-the-art curriculum learning (e.g, teacher-student, self-play) and automaton-guided reinforcement learning baselines (e.g, Q-Learning for Reward Machines). Further, we demonstrate that AGCL performs well even in the presence of noise in the task's OOMDP description, and also when distractor objects are present that are not modeled in the logical specification of the tasks' objectives.

Sumit Kumar Jha, Susmit Jha, Rickard Ewetz et al.

We present a comprehensive evaluation of the robustness and explainability of ResNet-like models in the context of Unintended Radiated Emission (URE) classification and suggest a new approach leveraging Neural Stochastic Differential Equations (SDEs) to address identified limitations. We provide an empirical demonstration of the fragility of ResNet-like models to Gaussian noise perturbations, where the model performance deteriorates sharply and its F1-score drops to near insignificance at 0.008 with a Gaussian noise of only 0.5 standard deviation. We also highlight a concerning discrepancy where the explanations provided by ResNet-like models do not reflect the inherent periodicity in the input data, a crucial attribute in URE detection from stable devices. In response to these findings, we propose a novel application of Neural SDEs to build models for URE classification that are not only robust to noise but also provide more meaningful and intuitive explanations. Neural SDE models maintain a high F1-score of 0.93 even when exposed to Gaussian noise with a standard deviation of 0.5, demonstrating superior resilience to ResNet models. Neural SDE models successfully recover the time-invariant or periodic horizontal bands from the input data, a feature that was conspicuously missing in the explanations generated by ResNet-like models. This advancement presents a small but significant step in the development of robust and interpretable models for real-world URE applications where data is inherently noisy and assurance arguments demand interpretable machine learning predictions.

Joshua Pickard, Ram Prakash, Marc Andrew Choi et al.

Recent advancements in Large Language Models (LLMs) are transforming biology, computer science, engineering, and every day life. However, integrating the wide array of computational tools, databases, and scientific literature continues to pose a challenge to biological research. LLMs are well-suited for unstructured integration, efficient information retrieval, and automating standard workflows and actions from these diverse resources. To harness these capabilities in bioinformatics, we present a prototype Bioinformatics Retrieval Augmented Digital assistant (BRAD). BRAD is a chatbot and agentic system that integrates a variety of bioinformatics tools. The Python package implements an AI \texttt{Agent} that is powered by LLMs and connects to a local file system, online databases, and a user's software. The \texttt{Agent} is highly configurable, enabling tasks such as Retrieval-Augmented Generation, searches across bioinformatics databases, and the execution of software pipelines. BRAD's coordinated integration of bioinformatics tools delivers a context-aware and semi-autonomous system that extends beyond the capabilities of conventional LLM-based chatbots. A graphical user interface (GUI) provides an intuitive interface to the system.

Suraj Singireddy, Precious Nwaorgu, Andre Beckus et al.

Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is prohibitively expensive, and the learned policies exhibit poor generalization on tasks outside the training data distribution. To mitigate these issues, we introduce automaton distillation, a form of neuro-symbolic transfer learning in which Q-value estimates from a teacher are distilled into a low-dimensional representation in the form of an automaton. We then propose methods for generating Q-value estimates where symbolic information is extracted from a teacher's Deep Q-Network (DQN). The resulting Q-value estimates are used to bootstrap learning in the target discrete and continuous environment via a modified DQN and Twin-Delayed Deep Deterministic (TD3) loss function, respectively. We demonstrate that automaton distillation decreases the time required to find optimal policies for various decision tasks in new environments, even in a target environment different in structure from the source environment.

Kamal Acharya, Alvaro Velasquez, Yongxin Liu et al.

Weather disaster related emergency operations pose a great challenge to air mobility in both aircraft and airport operations, especially when the impact is gradually approaching. We propose an optimized framework for adjusting airport operational schedules for such pre-disaster scenarios. We first, aggregate operational data from multiple airports and then determine the optimal count of evacuation flights to maximize the impacted airport's outgoing capacity without impeding regular air traffic. We then propose a novel Neural Network (NN) accelerated Genetic Algorithm(GA) for evacuation planning. Our experiments show that integration yielded comparable results but with smaller computational overhead. We find that the utilization of a NN enhances the efficiency of a GA, facilitating more rapid convergence even when operating with a reduced population size. This effectiveness persists even when the model is trained on data from airports different from those under test.

Ismail R. Alkhouri, George K. Atia, Alvaro Velasquez

The success of machine learning solutions for reasoning about discrete structures has brought attention to its adoption within combinatorial optimization algorithms. Such approaches generally rely on supervised learning by leveraging datasets of the combinatorial structures of interest drawn from some distribution of problem instances. Reinforcement learning has also been employed to find such structures. In this paper, we propose a radically different approach in that no data is required for training the neural networks that produce the solution. In particular, we reduce the combinatorial optimization problem to a neural network and employ a dataless training scheme to refine the parameters of the network such that those parameters yield the structure of interest. We consider the combinatorial optimization problems of finding maximum independent sets and maximum cliques in a graph. In principle, since these problems belong to the NP-hard complexity class, our proposed approach can be used to solve any other NP-hard problem. Additionally, we propose a universal graph reduction procedure to handle large scale graphs. The reduction exploits community detection for graph partitioning and is applicable to any graph type and/or density. Experimental evaluation on both synthetic graphs and real-world benchmarks demonstrates that our method performs on par with or outperforms state-of-the-art heuristic, reinforcement learning, and machine learning based methods without requiring any data.

Alexander Grushin, Walt Woods, Alvaro Velasquez et al.

Any autonomous controller will be unsafe in some situations. The ability to quantitatively identify when these unsafe situations are about to occur is crucial for drawing timely human oversight in, e.g., freight transportation applications. In this work, we demonstrate that the true criticality of an agent's situation can be robustly defined as the mean reduction in reward given some number of random actions. Proxy criticality metrics that are computable in real-time (i.e., without actually simulating the effects of random actions) can be compared to the true criticality, and we show how to leverage these proxy metrics to generate safety margins, which directly tie the consequences of potentially incorrect actions to an anticipated loss in overall performance. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment, and demonstrate how safety margins decrease as agents approach failure states. The integration of safety margins into programs for monitoring deployed agents allows for the real-time identification of potentially catastrophic situations.

Walt Woods, Alexander Grushin, Simon Khan et al.

AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in support of human decisions, relying on the AI control system in safe situations while calling on a human co-decider for critical situations. We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks, including MuZero. Multiple improvements to the base agent architecture are proposed. We demonstrate how this technology has two applications: for intelligent decision tools and to enhance training / learning frameworks. In a decision support context, adversarial explanations help a user make the correct decision by highlighting those contextual factors that would need to change for a different AI-recommended decision. As another benefit of adversarial explanations, we show that the learned AI control system demonstrates robustness against adversarial tampering. Additionally, we supplement AE by introducing strategically similar autoencoders (SSAs) to help users identify and understand all salient factors being considered by the AI system. In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction. Finally, to identify when AI decisions would most benefit from human oversight, we tie this combined system to our prior art on statistically verified analyses of the criticality of decisions at any point in time.

Alexander Grushin, Walt Woods, Alvaro Velasquez et al.

State of the art reinforcement learning methods sometimes encounter unsafe situations. Identifying when these situations occur is of interest both for post-hoc analysis and during deployment, where it might be advantageous to call out to a human overseer for help. Efforts to gauge the criticality of different points in time have been developed, but their accuracy is not well established due to a lack of ground truth, and they are not designed to be easily interpretable by end users. Therefore, we seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users. We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions. We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality. Safety margins make these interpretable, when defined as the number of random actions for which performance loss will not exceed some tolerance with high confidence. We demonstrate this approach in several environment-agent combinations; for an A3C agent in an Atari Beamrider environment, the lowest 5% of safety margins contain 47% of agent losses; i.e., supervising only 5% of decisions could potentially prevent roughly half of an agent's errors. This criticality framework measures the potential impacts of bad decisions, even before those decisions are made, allowing for more effective debugging and oversight of autonomous agents.

Hairi, Minghong Fang, Zifan Zhang et al.

In this paper, we study a fully-decentralized multi-agent policy evaluation problem, which is an important sub-problem in cooperative multi-agent reinforcement learning, in the presence of up to $f$ faulty agents. In particular, we focus on the so-called Byzantine faulty model with model poisoning setting. In general, policy evaluation is to evaluate the value function of any given policy. In cooperative multi-agent system, the system-wide rewards are usually modeled as the uniform average of rewards from all agents. We investigate the multi-agent policy evaluation problem in the presence of Byzantine agents, particularly in the setting of heterogeneous local rewards. Ideally, the goal of the agents is to evaluate the accumulated system-wide rewards, which are uniform average of rewards of the normal agents for a given policy. It means that all agents agree upon common values (the consensus part) and furthermore, the consensus values are the value functions (the convergence part). However, we prove that this goal is not achievable. Instead, we consider a relaxed version of the problem, where the goal of the agents is to evaluate accumulated system-wide reward, which is an appropriately weighted average reward of the normal agents. We further prove that there is no correct algorithm that can guarantee that the total number of positive weights exceeds $|\mathcal{N}|-f $, where $|\mathcal{N}|$ is the number of normal agents. Towards the end, we propose a Byzantine-tolerant decentralized temporal difference algorithm that can guarantee asymptotic consensus under scalar function approximation. We then empirically test the effective of the proposed algorithm.

Safayat Bin Hakim, Muhammad Adil, Alvaro Velasquez et al.

In this paper, we propose an Adaptive Neuro-Symbolic Learning and Reasoning Framework for digital twin technology called ``ANSR-DT." Digital twins in industrial environments often struggle with interpretability, real-time adaptation, and human input integration. Our approach addresses these challenges by combining CNN-LSTM dynamic event detection with reinforcement learning and symbolic reasoning to enable adaptive intelligence with interpretable decision processes. This integration enhances environmental understanding while promoting continuous learning, leading to more effective real-time decision-making in human-machine collaborative applications. We evaluated ANSR-DT on synthetic industrial data, observing significant improvements over traditional approaches, with up to 99.5% accuracy for dynamic pattern recognition. The framework demonstrated superior adaptability with extended reinforcement learning training, improving explained variance from 0.447 to 0.547. Future work aims at scaling to larger datasets to test rule management beyond the current 14 rules. Our open-source implementation promotes reproducibility and establishes a foundation for future research in adaptive, interpretable digital twins for industrial applications.

Jingxuan Zhu, Alec Koppel, Alvaro Velasquez et al.

In decentralized cooperative multi-armed bandits (MAB), each agent observes a distinct stream of rewards, and seeks to exchange information with others to select a sequence of arms so as to minimize its regret. Agents in the cooperative setting can outperform a single agent running a MAB method such as Upper-Confidence Bound (UCB) independently. In this work, we study how to recover such salient behavior when an unknown fraction of the agents can be Byzantine, that is, communicate arbitrarily wrong information in the form of reward mean-estimates or confidence sets. This framework can be used to model attackers in computer networks, instigators of offensive content into recommender systems, or manipulators of financial markets. Our key contribution is the development of a fully decentralized resilient upper confidence bound (UCB) algorithm that fuses an information mixing step among agents with a truncation of inconsistent and extreme values. This truncation step enables us to establish that the performance of each normal agent is no worse than the classic single-agent UCB1 algorithm in terms of regret, and more importantly, the cumulative regret of all normal agents is strictly better than the non-cooperative case, provided that each agent has at least 3f+1 neighbors where f is the maximum possible Byzantine agents in each agent's neighborhood. Extensions to time-varying neighbor graphs, and minimax lower bounds are further established on the achievable regret. Experiments corroborate the merits of this framework in practice.

Ismail Alkhouri, Cedric Le Denmat, Yingjie Li et al.

Combinatorial Optimization (CO) addresses many important problems, including the challenging Maximum Independent Set (MIS) problem. Alongside exact and heuristic solvers, differentiable approaches have emerged, often using continuous relaxations of ReLU-based or quadratic objectives. Noting that an MIS in a graph is a Maximum Clique (MC) in its complement, we propose a new quadratic formulation for MIS by incorporating an MC term, improving convergence and exploration. We show that every maximal independent set corresponds to a local minimizer, derive conditions with respect to the MIS size, and characterize stationary points. To tackle the non-convexity of the objective, we propose optimizing several initializations in parallel using momentum-based gradient descent, complemented by an efficient MIS checking criterion derived from our theory. We dub our method as parallelized Clique-Informed Quadratic Optimization for MIS (pCQO-MIS). Our experimental results demonstrate the effectiveness of the proposed method compared to exact, heuristic, sampling, and data-centric approaches. Notably, our method avoids the out-of-distribution tuning and reliance on (un)labeled data required by data-centric methods, while achieving superior MIS sizes and competitive runtime relative to their inference time. Additionally, a key advantage of pCQO-MIS is that, unlike exact and heuristic solvers, the runtime scales only with the number of nodes in the graph, not the number of edges. Our code is available at the GitHub repository: https://github.com/ledenmat/pCQO-mis-benchmark/tree/refactor.

Lekai Chen, Ashutosh Trivedi, Alvaro Velasquez

The emergence of intelligence in large language models (LLMs) has inspired investigations into their integration into automata learning. This paper introduces the probabilistic Minimally Adequate Teacher (pMAT) formulation, which leverages a probabilistic oracle that could give persistent errors randomly during answering the membership queries for deterministic finite automata (DFA) learning. Given the tendency of LLMs to produce hallucinatory content, we have developed techniques to improve answer accuracy and ensure the correctness of the learned automata. We propose the $\mathtt{Discrimination}$ prompt as well as the $\mathtt{Verification}$ prompt and explore their advantages over common prompts. Additionally, we compare DFA learning performance between the TTT algorithm and common active learning algorithms. To address the exponential number of persistent errors, we implement a dynamic query cache refinement algorithm that identifies and corrects conflicting queries by combining the active and passive learning algorithms. The empirical results demonstrate the robustness and efficiency of our approach, providing a theoretical foundation for automata learning with LLMs in the loop.

Longchao Da, Justin Turnau, Thirulogasankar Pranav Kutralingam et al.

Deep Reinforcement Learning (RL) has been explored and verified to be effective in solving decision-making tasks in various domains, such as robotics, transportation, recommender systems, etc. It learns from the interaction with environments and updates the policy using the collected experience. However, due to the limited real-world data and unbearable consequences of taking detrimental actions, the learning of RL policy is mainly restricted within the simulators. This practice guarantees safety in learning but introduces an inevitable sim-to-real gap in terms of deployment, thus causing degraded performance and risks in execution. There are attempts to solve the sim-to-real problems from different domains with various techniques, especially in the era with emerging techniques such as large foundations or language models that have cast light on the sim-to-real. This survey paper, to the best of our knowledge, is the first taxonomy that formally frames the sim-to-real techniques from key elements of the Markov Decision Process (State, Action, Transition, and Reward). Based on the framework, we cover comprehensive literature from the classic to the most advanced methods including the sim-to-real techniques empowered by foundation models, and we also discuss the specialties that are worth attention in different domains of sim-to-real problems. Then we summarize the formal evaluation process of sim-to-real performance with accessible code or benchmarks. The challenges and opportunities are also presented to encourage future exploration of this direction. We are actively maintaining a repository to include the most up-to-date sim-to-real research work to help domain researchers.

Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh et al.

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain vulnerable to jailbreak attacks. In this work, we first highlight an important safety gap to describe that alignment achieved solely through safety training may be insufficient against jailbreak attacks. To address this vulnerability, we propose Immune, an inference-time defense framework that leverages a safe reward model through controlled decoding to defend against jailbreak attacks. Additionally, we provide a mathematical characterization of Immune, offering insights on why it improves safety against jailbreaks. Extensive evaluations on diverse jailbreak benchmarks using recent MLLMs reveal that Immune effectively enhances model safety while preserving the model's original capabilities. For instance, against text-based jailbreak attacks on LLaVA-1.6, Immune reduces the attack success rate by 57.82% and 16.78% compared to the base MLLM and state-of-the-art defense strategy, respectively.

Justus Renkhoff, Ke Feng, Marc Meier-Doernberg et al.

Neurosymbolic artificial intelligence (AI) is an emerging branch of AI that combines the strengths of symbolic AI and sub-symbolic AI. A major drawback of sub-symbolic AI is that it acts as a "black box", meaning that predictions are difficult to explain, making the testing & evaluation (T&E) and validation & verification (V&V) processes of a system that uses sub-symbolic AI a challenge. Since neurosymbolic AI combines the advantages of both symbolic and sub-symbolic AI, this survey explores how neurosymbolic applications can ease the V&V process. This survey considers two taxonomies of neurosymbolic AI, evaluates them, and analyzes which algorithms are commonly used as the symbolic and sub-symbolic components in current applications. Additionally, an overview of current techniques for the T&E and V&V processes of these components is provided. Furthermore, it is investigated how the symbolic part is used for T&E and V&V purposes in current neurosymbolic applications. Our research shows that neurosymbolic AI as great potential to ease the T&E and V&V processes of sub-symbolic AI by leveraging the possibilities of symbolic AI. Additionally, the applicability of current T&E and V&V methods to neurosymbolic AI is assessed, and how different neurosymbolic architectures can impact these methods is explored. It is found that current T&E and V&V techniques are partly sufficient to test, evaluate, verify, or validate the symbolic and sub-symbolic part of neurosymbolic applications independently, while some of them use approaches where current T&E and V&V methods are not applicable by default, and adjustments or even new approaches are needed. Our research shows that there is great potential in using symbolic AI to test, evaluate, verify, or validate the predictions of a sub-symbolic model, making neurosymbolic AI an interesting research direction for safe, secure, and trustworthy AI.

Milad Kazemi, Mateo Perez, Fabio Somenzi et al.

We present a modular approach to \emph{reinforcement learning} (RL) in environments consisting of simpler components evolving in parallel. A monolithic view of such modular environments may be prohibitively large to learn, or may require unrealizable communication between the components in the form of a centralized controller. Our proposed approach is based on the assume-guarantee paradigm where the optimal control for the individual components is synthesized in isolation by making \emph{assumptions} about the behaviors of neighboring components, and providing \emph{guarantees} about their own behavior. We express these \emph{assume-guarantee contracts} as regular languages and provide automatic translations to scalar rewards to be used in RL. By combining local probabilities of satisfaction for each component, we provide a lower bound on the probability of satisfaction of the complete system. By solving a Markov game for each component, RL can produce a controller for each component that maximizes this lower bound. The controller utilizes the information it receives through communication, observations, and any knowledge of a coarse model of other agents. We experimentally demonstrate the efficiency of the proposed approach on a variety of case studies.

Erfaun Noorani, Zachary Serlin, Ben Price et al.

The DARPA Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT) program aims to address rapid and robust transfer of autonomy technologies across dynamic and complex environments, goals, and platforms. Existing methods for simulation-to-reality (sim-to-real) transfer often rely on high-fidelity simulations and struggle with broad adaptation, particularly in time-sensitive scenarios. Although many approaches have shown incredible performance at specific tasks, most techniques fall short when posed with unforeseen, complex, and dynamic real-world scenarios due to the inherent limitations of simulation. In contrast to current research that aims to bridge the gap between simulation environments and the real world through increasingly sophisticated simulations and a combination of methods typically assuming a small sim-to-real gap -- such as domain randomization, domain adaptation, imitation learning, meta-learning, policy distillation, and dynamic optimization -- TIAMAT takes a different approach by instead emphasizing transfer and adaptation of the autonomy stack directly to real-world environments by utilizing a breadth of low(er)-fidelity simulations to create broadly effective sim-to-real transfers. By abstractly learning from multiple simulation environments in reference to their shared semantics, TIAMAT's approaches aim to achieve abstract-to-real transfer for effective and rapid real-world adaptation. Furthermore, this program endeavors to improve the overall autonomy pipeline by addressing the inherent challenges in translating simulated behaviors into effective real-world performance.

Myeung Suk Oh, Zhiyao Zhang, FNU Hairi et al.

With wireless devices increasingly forming a unified smart network for seamless, user-friendly operations, random access (RA) medium access control (MAC) design is considered a key solution for handling unpredictable data traffic from multiple terminals. However, it remains challenging to design an effective RA-based MAC protocol to minimize collisions and ensure transmission fairness across the devices. While existing multi-agent reinforcement learning (MARL) approaches with centralized training and decentralized execution (CTDE) have been proposed to optimize RA performance, their reliance on centralized training and the significant overhead required for information collection can make real-world applications unrealistic. In this work, we adopt a fully decentralized MARL architecture, where policy learning does not rely on centralized tasks but leverages consensus-based information exchanges across devices. We design our MARL algorithm over an actor-critic (AC) network and propose exchanging only local rewards to minimize communication overhead. Furthermore, we provide a theoretical proof of global convergence for our approach. Numerical experiments show that our proposed MARL algorithm can significantly improve RA network performance compared to other baselines.

Milad Kazemi, Mateo Perez, Fabio Somenzi et al.

Recent advances in reinforcement learning (RL) have renewed focus on the design of reward functions that shape agent behavior. Manually designing reward functions is tedious and error-prone. A principled alternative is to specify behaviors in a formal language that can be automatically translated into rewards. Omega-regular languages are a natural choice for this purpose, given their established role in formal verification and synthesis. However, existing methods using omega-regular specifications typically rely on discounted reward RL in episodic settings, with periodic resets. This setup misaligns with the semantics of omega-regular specifications, which describe properties over infinite behavior traces. In such cases, the average reward criterion and the continuing setting -- where the agent interacts with the environment over a single, uninterrupted lifetime -- are more appropriate. To address the challenges of infinite-horizon, continuing tasks, we focus on absolute liveness specifications -- a subclass of omega-regular languages that cannot be violated by any finite behavior prefix, making them well-suited to the continuing setting. We present the first model-free RL framework that translates absolute liveness specifications to average-reward objectives. Our approach enables learning in communicating MDPs without episodic resetting. We also introduce a reward structure for lexicographic multi-objective optimization, aiming to maximize an external average-reward objective among the policies that also maximize the satisfaction probability of a given omega-regular specification. Our method guarantees convergence in unknown communicating MDPs and supports on-the-fly reductions that do not require full knowledge of the environment, thus enabling model-free RL. Empirical results show our average-reward approach in continuing setting outperforms discount-based methods across benchmarks.

Weilin Xu, Sebastian Szyller, Cory Cornelius et al.

Adversarial examples in the digital domain against deep learning-based computer vision models allow for perturbations that are imperceptible to human eyes. However, producing similar adversarial examples in the physical world has been difficult due to the non-differentiable image distortion functions in visual sensing systems. The existing algorithms for generating physically realizable adversarial examples often loosen their definition of adversarial examples by allowing unbounded perturbations, resulting in obvious or even strange visual patterns. In this work, we make adversarial examples imperceptible in the physical world using a straight-through estimator (STE, a.k.a. BPDA). We employ STE to overcome the non-differentiability -- applying exact, non-differentiable distortions in the forward pass of the backpropagation step, and using the identity function in the backward pass. Our differentiable rendering extension to STE also enables imperceptible adversarial patches in the physical world. Using printout photos, and experiments in the CARLA simulator, we show that STE enables fast generation of $\ell_\infty$ bounded adversarial examples despite the non-differentiable distortions. To the best of our knowledge, this is the first work demonstrating imperceptible adversarial examples bounded by small $\ell_\infty$ norms in the physical world that force zero classification accuracy in the global perturbation threat model and cause near-zero ($4.22\%$) AP50 in object detection in the patch perturbation threat model. We urge the community to re-evaluate the threat of adversarial examples in the physical world.

Huu Binh Ta, Michael Cardei, Alvaro Velasquez et al.

Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for structured and symbolic generation. However, standard training targets a likelihood-based objective that primarily matches the data distribution and provides no native mechanism for enforcing hard constraints or optimizing non-differentiable properties at inference time. This work addresses this limitation and introduces Search-Augmented Masked Diffusion (SearchDiff), a training-free neurosymbolic inference framework that integrates informed search directly into the reverse denoising process. At each denoising step, the model predictions define a proposal set that is optimized under a user-specified property satisfaction, yielding a modified reverse transition that steers sampling toward probable and feasible solutions. Experiments in biological design and symbolic reasoning illustrate that SearchDiff substantially improves constraint satisfaction and property adherence, while consistently outperforming discrete diffusion and autoregressive baselines.

Mahyar Alinejad, Alvaro Velasquez, Yue Wang et al.

Reinforcement Learning (RL) in environments with complex, history-dependent reward structures poses significant challenges for traditional methods. In this work, we introduce a novel approach that leverages automaton-based feedback to guide the learning process, replacing explicit reward functions with preferences derived from a deterministic finite automaton (DFA). Unlike conventional approaches that use automata for direct reward specification, our method employs the structure of the DFA to generate preferences over trajectories that are used to learn a reward function, eliminating the need for manual reward engineering. Our framework introduces a static approach that uses the learned reward function directly for policy optimization and a dynamic approach that involves continuous refining of the reward function and policy through iterative updates until convergence. Our experiments in both discrete and continuous environments demonstrate that our approach enables the RL agent to learn effective policies for tasks with temporal dependencies, outperforming traditional reward engineering and automaton-based baselines such as reward machines and LTL-guided methods. Our results highlight the advantages of automaton-based preferences in handling non-Markovian rewards, offering a scalable, efficient, and human-independent alternative to traditional reward modeling. We also provide a convergence guarantee showing that under standard assumptions our automaton-guided preference-based framework learns a policy that is near-optimal with respect to the true non-Markovian objective.

Safayat Bin Hakim, Muhammad Adil, Alvaro Velasquez et al.

Traditional Artificial Intelligence (AI) approaches in cybersecurity exhibit fundamental limitations: inadequate conceptual grounding leading to non-robustness against novel attacks; limited instructibility impeding analyst-guided adaptation; and misalignment with cybersecurity objectives. Neuro-Symbolic (NeSy) AI has emerged with the potential to revolutionize cybersecurity AI. However, there is no systematic understanding of this emerging approach. These hybrid systems address critical cybersecurity challenges by combining neural pattern recognition with symbolic reasoning, enabling enhanced threat understanding while introducing concerning autonomous offensive capabilities that reshape threat landscapes. In this survey, we systematically characterize this field by analyzing 127 publications spanning 2019-July 2025. We introduce a Grounding-Instructibility-Alignment (G-I-A) framework to evaluate these systems, focusing on both cyber defense and cyber offense across network security, malware analysis, and cyber operations. Our analysis shows advantages of multi-agent NeSy architectures and identifies critical implementation challenges including standardization gaps, computational complexity, and human-AI collaboration requirements that constrain deployment. We show that causal reasoning integration is the most transformative advancement, enabling proactive defense beyond correlation-based approaches. Our findings highlight dual-use implications where autonomous systems demonstrate substantial capabilities in zero-day exploitation while achieving significant cost reductions, altering threat dynamics. We provide insights and future research directions, emphasizing the urgent need for community-driven standardization frameworks and responsible development practices that ensure advancement serves defensive cybersecurity objectives while maintaining societal alignment.

Yunhao Yang, Neel P. Bhatt, Christian Ellis et al.

Logistics operators, from battlefield coordinators rerouting airlifts ahead of a storm to warehouse managers juggling late trucks, often face life-critical decisions that demand both domain expertise and rapid and continuous replanning. While popular methods like integer programming yield logistics plans that satisfy user-defined logical constraints, they are slow and assume an idealized mathematical model of the environment that does not account for uncertainty. On the other hand, large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry by translating free-form utterances into executable plans, yet they remain prone to misinterpretations and hallucinations that jeopardize safety and cost. We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation. It converts user requests into structured planning specifications, quantifies its own uncertainty at the field and token level, and invokes an interactive clarification loop whenever confidence falls below an adaptive threshold. A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%. These preliminary results highlight a practical path toward certifiable, real-time, and user-aligned decision-making for complex logistics.

Safayat Bin Hakim, Muhammad Adil, Alvaro Velasquez et al.

Current Retrieval-Augmented Generation systems use uniform processing, causing inefficiency as simple queries consume resources similar to complex multi-hop tasks. We present SymRAG, a framework that introduces adaptive query routing via real-time complexity and load assessment to select symbolic, neural, or hybrid pathways. SymRAG's neuro-symbolic approach adjusts computational pathways based on both query characteristics and system load, enabling efficient resource allocation across diverse query types. By combining linguistic and structural query properties with system load metrics, SymRAG allocates resources proportional to reasoning requirements. Evaluated on 2,000 queries across HotpotQA (multi-hop reasoning) and DROP (discrete reasoning) using Llama-3.2-3B and Mistral-7B models, SymRAG achieves competitive accuracy (97.6--100.0% exact match) with efficient resource utilization (3.6--6.2% CPU utilization, 0.985--3.165s processing). Disabling adaptive routing increases processing time by 169--1151%, showing its significance for complex models. These results suggest adaptive computation strategies are more sustainable and scalable for hybrid AI systems that use dynamic routing and neuro-symbolic frameworks.

Ayush Gupta, Anirban Roy, Rama Chellappa et al. · amazon-science

We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question, we generate an open-ended answer grounded with the start and end time. For this task, we propose TOGA: a vision-language model for Temporally Grounded Open-Ended Video QA with Weak Supervision. We instruct-tune TOGA to jointly generate the answer and the temporal grounding. We operate in a weakly supervised setup where the temporal grounding annotations are not available. We generate pseudo labels for temporal grounding and ensure the validity of these labels by imposing a consistency constraint between the question of a grounding response and the response generated by a question referring to the same temporal segment. We notice that jointly generating the answers with the grounding improves performance on question answering as well as grounding. We evaluate TOGA on grounded QA and open-ended QA tasks. For grounded QA, we consider the NExT-GQA benchmark which is designed to evaluate weakly supervised grounded question answering. For open-ended QA, we consider the MSVD-QA and ActivityNet-QA benchmarks. We achieve state-of-the-art performance for both tasks on these benchmarks.

Gabriel Maliakal, Ismail Alkhouri, Alvaro Velasquez et al.

The Maximum Cut (MaxCut) problem is NP-Complete, and obtaining its optimal solution is NP-hard in the worst case. As a result, heuristic-based algorithms are commonly used, though their design often requires significant domain expertise. More recently, learning-based methods trained on large (un)labeled datasets have been proposed; however, these approaches often struggle with generalizability and scalability. A well-known approximation algorithm for MaxCut is the Goemans-Williamson (GW) algorithm, which relaxes the Quadratic Unconstrained Binary Optimization (QUBO) formulation into a semidefinite program (SDP). The GW algorithm then applies hyperplane rounding by uniformly sampling a random hyperplane to convert the SDP solution into binary node assignments. In this paper, we propose a training-data-free approach based on a non-episodic reinforcement learning formulation, in which an agent learns to select improved rounding hyperplanes that yield better cuts than those produced by the GW algorithm. By optimizing over a Markov Decision Process (MDP), our method consistently achieves better cuts across large-scale graphs with varying densities and degree distributions.

Noah Topper, Alvaro Velasquez, George Atia

Inverse reinforcement learning (IRL) is the problem of inferring a reward function from expert behavior. There are several approaches to IRL, but most are designed to learn a Markovian reward. However, a reward function might be non-Markovian, depending on more than just the current state, such as a reward machine (RM). Although there has been recent work on inferring RMs, it assumes access to the reward signal, absent in IRL. We propose a Bayesian IRL (BIRL) framework for inferring RMs directly from expert behavior, requiring significant changes to the standard framework. We define a new reward space, adapt the expert demonstration to include history, show how to compute the reward posterior, and propose a novel modification to simulated annealing to maximize this posterior. We demonstrate that our method performs well when optimizing according to its inferred reward and compares favorably to an existing method that learns exclusively binary non-Markovian rewards.

Prathyush Poduval, Zhuowen Zou, Alvaro Velasquez et al.

This paper presents a quantum algorithm for efficiently decoding hypervectors, a crucial process in extracting atomic elements from hypervectors - an essential task in Hyperdimensional Computing (HDC) models for interpretable learning and information retrieval. HDC employs high-dimensional vectors and efficient operators to encode and manipulate information, representing complex objects from atomic concepts. When one attempts to decode a hypervector that is the product (binding) of multiple hypervectors, the factorization becomes prohibitively costly with classical optimization-based methods and specialized recurrent networks, an inherent consequence of the binding operation. We propose HDQF, an innovative quantum computing approach, to address this challenge. By exploiting parallels between HDC and quantum computing and capitalizing on quantum algorithms' speedup capabilities, HDQF encodes potential factors as a quantum superposition using qubit states and bipolar vector representation. This yields a quadratic speedup over classical search methods and effectively mitigates Hypervector Factorization capacity issues.

Yash Shukla, Tanushree Burman, Abhishek Kulkarni et al.

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample complexity issues, recent approaches have used high-level task specifications, such as Linear Temporal Logic (LTL$_f$) formulas or Reward Machines (RM), to guide the learning progress of the agent. In this work, we propose a novel approach, called Logical Specifications-guided Dynamic Task Sampling (LSTS), that learns a set of RL policies to guide an agent from an initial state to a goal state based on a high-level task specification, while minimizing the number of environmental interactions. Unlike previous work, LSTS does not assume information about the environment dynamics or the Reward Machine, and dynamically samples promising tasks that lead to successful goal policies. We evaluate LSTS on a gridworld and show that it achieves improved time-to-threshold performance on complex sequential decision-making problems compared to state-of-the-art RM and Automaton-guided RL baselines, such as Q-Learning for Reward Machines and Compositional RL from logical Specifications (DIRL). Moreover, we demonstrate that our method outperforms RM and Automaton-guided RL baselines in terms of sample-efficiency, both in a partially observable robotic task and in a continuous control robotic manipulation task.

K. Acharya, W. Raza, C. M. J. M. Dourado et al.

The area of Neurosymbolic Artificial Intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing sub-fields such as Neurosymbolic Deep Learning (Neurosymbolic DL) and Neurosymbolic Reinforcement Learning (Neurosymbolic RL). Compared to traditional learning methods, Neurosymbolic AI offers significant advantages by simplifying complexity and providing transparency and explainability. Reinforcement Learning(RL), a long-standing Artificial Intelligence(AI) concept that mimics human behavior using rewards and punishment, is a fundamental component of Neurosymbolic RL, a recent integration of the two fields that has yielded promising results. The aim of this paper is to contribute to the emerging field of Neurosymbolic RL by conducting a literature survey. Our evaluation focuses on the three components that constitute Neurosymbolic RL: neural, symbolic, and RL. We categorize works based on the role played by the neural and symbolic parts in RL, into three taxonomies:Learning for Reasoning, Reasoning for Learning and Learning-Reasoning. These categories are further divided into sub-categories based on their applications. Furthermore, we analyze the RL components of each research work, including the state space, action space, policy module, and RL algorithm. Additionally, we identify research opportunities and challenges in various applications within this dynamic field.

Yue Wang, Alvaro Velasquez, George Atia et al.

Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under the model-free setting. We first theoretically characterize the structure of solutions to the robust average-reward Bellman equation, which is essential for our later convergence analysis. We then design two model-free algorithms, robust relative value iteration (RVI) TD and robust RVI Q-learning, and theoretically prove their convergence to the optimal solution. We provide several widely used uncertainty sets as examples, including those defined by the contamination model, total variation, Chi-squared divergence, Kullback-Leibler (KL) divergence and Wasserstein distance.

Sumit Kumar Jha, Arvind Ramanathan, Rickard Ewetz et al.

Deep neural networks such as AlphaFold and RoseTTAFold predict remarkably accurate structures of proteins compared to other algorithmic approaches. It is known that biologically small perturbations in the protein sequence do not lead to drastic changes in the protein structure. In this paper, we demonstrate that RoseTTAFold does not exhibit such a robustness despite its high accuracy, and biologically small perturbations for some input sequences result in radically different predicted protein structures. This raises the challenge of detecting when these predicted protein structures cannot be trusted. We define the robustness measure for the predicted structure of a protein sequence to be the inverse of the root-mean-square distance (RMSD) in the predicted structure and the structure of its adversarially perturbed sequence. We use adversarial attack methods to create adversarial protein sequences, and show that the RMSD in the predicted protein structure ranges from 0.119Å to 34.162Å when the adversarial perturbations are bounded by 20 units in the BLOSUM62 distance. This demonstrates very high variance in the robustness measure of the predicted structures. We show that the magnitude of the correlation (0.917) between our robustness measure and the RMSD between the predicted structure and the ground truth is high, that is, the predictions with low robustness measure cannot be trusted. This is the first paper demonstrating the susceptibility of RoseTTAFold to adversarial attacks.

Edward Verenich, Tobias Martin, Alvaro Velasquez et al.

Convolutional neural networks (CNN) are now being widely used for classifying and detecting pulmonary abnormalities in chest radiographs. Two complementary generalization properties of CNNs, translation invariance and equivariance, are particularly useful in detecting manifested abnormalities associated with pulmonary disease, regardless of their spatial locations within the image. However, these properties also come with the loss of exact spatial information and global relative positions of abnormalities detected in local regions. Global relative positions of such abnormalities may help distinguish similar conditions, such as COVID-19 and viral pneumonia. In such instances, a global attention mechanism is needed, which CNNs do not support in their traditional architectures that aim for generalization afforded by translation invariance and equivariance. Vision Transformers provide a global attention mechanism, but lack translation invariance and equivariance, requiring significantly more training data samples to match generalization of CNNs. To address the loss of spatial information and global relations between features, while preserving the inductive biases of CNNs, we present a novel technique that serves as an auxiliary attention mechanism to existing CNN architectures, in order to extract global correlations between salient features.

Ismail R. Alkhouri, Alvaro Velasquez, George K. Atia

The design of additive imperceptible perturbations to the inputs of deep classifiers to maximize their misclassification rates is a central focus of adversarial machine learning. An alternative approach is to synthesize adversarial examples from scratch using GAN-like structures, albeit with the use of large amounts of training data. By contrast, this paper considers one-shot synthesis of adversarial examples; the inputs are synthesized from scratch to induce arbitrary soft predictions at the output of pre-trained models, while simultaneously maintaining high similarity to specified inputs. To this end, we present a problem that encodes objectives on the distance between the desired and output distributions of the trained model and the similarity between such inputs and the synthesized examples. We prove that the formulated problem is NP-complete. Then, we advance a generative approach to the solution in which the adversarial examples are obtained as the output of a generative network whose parameters are iteratively updated by optimizing surrogate loss functions for the dual-objective. We demonstrate the generality and versatility of the framework and approach proposed through applications to the design of targeted adversarial attacks, generation of decision boundary samples, and synthesis of low confidence classification inputs. The approach is further extended to an ensemble of models with different soft output specifications. The experimental results verify that the targeted and confidence reduction attack methods developed perform on par with state-of-the-art algorithms.

Taylor Dohmen, Noah Topper, George Atia et al.

The success of reinforcement learning in typical settings is predicated on Markovian assumptions on the reward signal by which an agent learns optimal policies. In recent years, the use of reward machines has relaxed this assumption by enabling a structured representation of non-Markovian rewards. In particular, such representations can be used to augment the state space of the underlying decision process, thereby facilitating non-Markovian reinforcement learning. However, these reward machines cannot capture the semantics of stochastic reward signals. In this paper, we make progress on this front by introducing probabilistic reward machines (PRMs) as a representation of non-Markovian stochastic rewards. We present an algorithm to learn PRMs from the underlying decision process and prove results around its correctness and convergence.

Alvaro Velasquez, Ismail Alkhouri, Andre Beckus et al.

Given a Markov decision process (MDP) and a linear-time ($ω$-regular or LTL) specification, the controller synthesis problem aims to compute the optimal policy that satisfies the specification. More recently, problems that reason over the asymptotic behavior of systems have been proposed through the lens of steady-state planning. This entails finding a control policy for an MDP such that the Markov chain induced by the solution policy satisfies a given set of constraints on its steady-state distribution. This paper studies a generalization of the controller synthesis problem for a linear-time specification under steady-state constraints on the asymptotic behavior. We present an algorithm to find a deterministic policy satisfying $ω$-regular and steady-state constraints by characterizing the solutions as an integer linear program, and experimentally evaluate our approach.

George K. Atia, Andre Beckus, Ismail Alkhouri et al.

The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined logic. While many such logics have been proposed with varying degrees of expressiveness and complexity in their capacity to capture desirable agent behavior, their value is limited when deriving decision-making policies which satisfy certain types of asymptotic behavior in general system models. In particular, we are interested in specifying constraints on the steady-state behavior of an agent, which captures the proportion of time an agent spends in each state as it interacts for an indefinite period of time with its environment. This is sometimes called the average or expected behavior of the agent and the associated planning problem is faced with significant challenges unless strong restrictions are imposed on the underlying model in terms of the connectivity of its graph structure. In this paper, we explore this steady-state planning problem that consists of deriving a decision-making policy for an agent such that constraints on its steady-state behavior are satisfied. A linear programming solution for the general case of multichain Markov Decision Processes (MDPs) is proposed and we prove that optimal solutions to the proposed programs yield stationary policies with rigorous guarantees of behavior.