Piyush Gupta

Sukriti Verma, Ayush Chopra, Jayakumar Subramanian et al.

The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures eventual consistency between the two. Various strategies have been introduced in literature to learn better gradient estimates to help achieve better convergence. Since gradient estimates depend upon the critic, we posit that improving the critic can provide a better gradient estimate for the actor at each time. Utilizing this, we propose Soft Actor Retrospective Critic (SARC), where we augment the SAC critic loss with another loss term - retrospective loss - leading to faster critic convergence and consequently, better policy gradient estimates for the actor. An existing implementation of SAC can be easily adapted to SARC with minimal modifications. Through extensive experimentation and analysis, we show that SARC provides consistent improvement over SAC on benchmark environments. We plan to open-source the code and all experiment data at: https://github.com/sukritiverma1996/SARC.

Piyush Gupta, Vaibhav Srivastava

We propose Deterministic Sequencing of Exploration and Exploitation (DSEE) algorithm with interleaving exploration and exploitation epochs for model-based RL problems that aim to simultaneously learn the system model, i.e., a Markov decision process (MDP), and the associated optimal policy. During exploration, DSEE explores the environment and updates the estimates for expected reward and transition probabilities. During exploitation, the latest estimates of the expected reward and transition probabilities are used to obtain a robust policy with high probability. We design the lengths of the exploration and exploitation epochs such that the cumulative regret grows as a sub-linear function of time.

Chak Lam Shek, Faizan M. Tariq, Sangjae Bae et al.

Heterogeneous multi-robot systems are increasingly deployed in long-horizon missions that require coordination among robots with diverse capabilities. However, existing planning approaches struggle to construct accurate symbolic representations and maintain plan consistency in dynamic environments. Classical PDDL planners require manually crafted symbolic models, while LLM-based planners often ignore agent heterogeneity and environmental uncertainty. We introduce KGLAMP, a knowledge-graph-guided LLM planning framework for heterogeneous multi-robot teams. The framework maintains a structured knowledge graph encoding object relations, spatial reachability, and robot capabilities, which guides the LLM in generating accurate PDDL problem specifications. The knowledge graph serves as a persistent, dynamically updated memory that incorporates new observations and triggers replanning upon detecting inconsistencies, enabling symbolic plans to adapt to evolving world states. Experiments on the MAT-THOR benchmark show that KGLAMP improves performance by at least 25.5% over both LLM-only and PDDL-based variants.

Piyush Gupta, David Isele, Enna Sachdeva et al.

We present a novel mission-planning strategy for heterogeneous multi-robot teams, taking into account the specific constraints and capabilities of each robot. Our approach employs hierarchical trees to systematically break down complex missions into manageable sub-tasks. We develop specialized APIs and tools, which are utilized by Large Language Models (LLMs) to efficiently construct these hierarchical trees. Once the hierarchical tree is generated, it is further decomposed to create optimized schedules for each robot, ensuring adherence to their individual constraints and capabilities. We demonstrate the effectiveness of our framework through detailed examples covering a wide range of missions, showcasing its flexibility and scalability.

Piyush Gupta, David Isele, Sangjae Bae

Real-world driving involves intricate interactions among vehicles navigating through dense traffic scenarios. Recent research focuses on enhancing the interaction awareness of autonomous vehicles to leverage these interactions in decision-making. These interaction-aware planners rely on neural-network-based prediction models to capture inter-vehicle interactions, aiming to integrate these predictions with traditional control techniques such as Model Predictive Control. However, this integration of deep learning-based models with traditional control paradigms often results in computationally demanding optimization problems, relying on heuristic methods. This study introduces a principled and efficient method for combining deep learning with constrained optimization, employing knowledge distillation to train smaller and more efficient networks, thereby mitigating complexity. We demonstrate that these refined networks maintain the problem-solving efficacy of larger models while significantly accelerating optimization. Specifically, in the domain of interaction-aware trajectory planning for autonomous vehicles, we illustrate that training a smaller prediction network using knowledge distillation speeds up optimization without sacrificing accuracy.

Haoqiang Kang, Enna Sachdeva, Piyush Gupta et al.

Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques like Proximal Policy Optimization (PPO), present notable limitations: SFT assumes Independent and Identically Distributed (IID) data, while PPO focuses on maximizing cumulative rewards. These limitations often restrict solution diversity and hinder generalization in multi-step reasoning tasks. To address these challenges, we introduce a novel framework, GFlowVLM, a framework that fine-tune VLMs using Generative Flow Networks (GFlowNets) to promote generation of diverse solutions for complex reasoning tasks. GFlowVLM models the environment as a non-Markovian decision process, allowing it to capture long-term dependencies essential for real-world applications. It takes observations and task descriptions as inputs to prompt chain-of-thought (CoT) reasoning which subsequently guides action selection. We use task based rewards to fine-tune VLM with GFlowNets. This approach enables VLMs to outperform prior fine-tuning methods, including SFT and RL. Empirical results demonstrate the effectiveness of GFlowVLM on complex tasks such as card games (NumberLine, BlackJack) and embodied planning tasks (ALFWorld), showing enhanced training efficiency, solution diversity, and stronger generalization capabilities across both in-distribution and out-of-distribution scenarios.

Piyush Gupta, Sangjae Bae, David Isele

The adoption of Large Language Models (LLMs) is rapidly expanding across various tasks that involve inherent graphical structures. Graphs are integral to a wide range of applications, including motion planning for autonomous vehicles, social networks, scene understanding, and knowledge graphs. Many problems, even those not initially perceived as graph-based, can be effectively addressed through graph theory. However, when applied to these tasks, LLMs often encounter challenges, such as hallucinations and mathematical inaccuracies. To overcome these limitations, we propose Graph-Grounded LLMs, a system that improves LLM performance on graph-related tasks by integrating a graph library through function calls. By grounding LLMs in this manner, we demonstrate significant reductions in hallucinations and improved mathematical accuracy in solving graph-based problems, as evidenced by the performance on the NLGraph benchmark. Finally, we showcase a disaster rescue application where the Graph-Grounded LLM acts as a decision-support system.

Piyush Gupta, Vaibhav Srivastava

We study optimal fidelity selection for a human operator servicing a queue of homogeneous tasks. The agent can service a task with a normal or high fidelity level, where fidelity refers to the degree of exactness and precision while servicing the task. Therefore, high-fidelity servicing results in higher-quality service but leads to larger service times and increased operator tiredness. We treat the human cognitive state as a lumped parameter that captures psychological factors such as workload and fatigue. The operator's service time distribution depends on her cognitive dynamics and the fidelity level selected for servicing the task. Her cognitive dynamics evolve as a Markov chain in which the cognitive state increases with high probability whenever she is busy and decreases while resting. The tasks arrive according to a Poisson process and the operator is penalized at a fixed rate for each task waiting in the queue. We address the trade-off between high-quality service of the task and consequent penalty due to a subsequent increase in queue length using a discrete-time Semi-Markov Decision Process framework. We numerically determine an optimal policy and the corresponding optimal value function. Finally, we establish the structural properties of an optimal fidelity policy and provide conditions under which the optimal policy is a threshold-based policy.

Sukriti Verma, Nikaash Puri, Piyush Gupta et al.

Explaining the behavior of black box machine learning models through human interpretable rules is an important research area. Recent work has focused on explaining model behavior locally i.e. for specific predictions as well as globally across the fields of vision, natural language, reinforcement learning and data science. We present a novel model-agnostic approach that derives rules to globally explain the behavior of classification models trained on numerical and/or categorical data. Our approach builds on top of existing local model explanation methods to extract conditions important for explaining model behavior for specific instances followed by an evolutionary algorithm that optimizes an information theory based fitness function to construct rules that explain global model behavior. We show how our approach outperforms existing approaches on a variety of datasets. Further, we introduce a parameter to evaluate the quality of interpretation under the scenario of distributional shift. This parameter evaluates how well the interpretation can predict model behavior for previously unseen data distributions. We show how existing approaches for interpreting models globally lack distributional robustness. Finally, we show how the quality of the interpretation can be improved under the scenario of distributional shift by adding out of distribution samples to the dataset used to learn the interpretation and thereby, increase robustness. All of the datasets used in our paper are open and publicly available. Our approach has been deployed in a leading digital marketing suite of products.

Nikita Mehrotra, Navdha Agarwal, Piyush Gupta et al.

Code clones are duplicate code fragments that share (nearly) similar syntax or semantics. Code clone detection plays an important role in software maintenance, code refactoring, and reuse. A substantial amount of research has been conducted in the past to detect clones. A majority of these approaches use lexical and syntactic information to detect clones. However, only a few of them target semantic clones. Recently, motivated by the success of deep learning models in other fields, including natural language processing and computer vision, researchers have attempted to adopt deep learning techniques to detect code clones. These approaches use lexical information (tokens) and(or) syntactic structures like abstract syntax trees (ASTs) to detect code clones. However, they do not make sufficient use of the available structural and semantic information hence, limiting their capabilities. This paper addresses the problem of semantic code clone detection using program dependency graphs and geometric neural networks, leveraging the structured syntactic and semantic information. We have developed a prototype tool HOLMES, based on our novel approach, and empirically evaluated it on popular code clone benchmarks. Our results show that HOLMES performs considerably better than the other state-of-the-art tool, TBCCD. We also evaluated HOLMES on unseen projects and performed cross dataset experiments to assess the generalizability of HOLMES. Our results affirm that HOLMES outperforms TBCCD since most of the pairs that HOLMES detected were either undetected or suboptimally reported by TBCCD.

Anubha Kabra, Ayush Chopra, Nikaash Puri et al.

Training a classification model on a dataset where the instances of one class outnumber those of the other class is a challenging problem. Such imbalanced datasets are standard in real-world situations such as fraud detection, medical diagnosis, and computational advertising. We propose an iterative data augmentation method, MixBoost, which intelligently selects (Boost) and then combines (Mix) instances from the majority and minority classes to generate synthetic hybrid instances that have characteristics of both classes. We evaluate MixBoost on 20 benchmark datasets, show that it outperforms existing approaches, and test its efficacy through significance testing. We also present ablation studies to analyze the impact of the different components of MixBoost.

Surgan Jandial, Ayush Chopra, Mausoom Sarkar et al.

Deep neural networks (DNNs) are powerful learning machines that have enabled breakthroughs in several domains. In this work, we introduce a new retrospective loss to improve the training of deep neural network models by utilizing the prior experience available in past model states during training. Minimizing the retrospective loss, along with the task-specific loss, pushes the parameter state at the current training step towards the optimal parameter state while pulling it away from the parameter state at a previous training step. Although a simple idea, we analyze the method as well as to conduct comprehensive sets of experiments across domains - images, speech, text, and graphs - to show that the proposed loss results in improved performance across input domains, tasks, and architectures.

Piyush Gupta, Demetris Coleman, Joshua E. Siegel

Automated vehicles' neural networks suffer from overfit, poor generalizability, and untrained edge cases due to limited data availability. Researchers synthesize randomized edge-case scenarios to assist in the training process, though simulation introduces potential for overfit to latent rules and features. Automating worst-case scenario generation could yield informative data for improving self driving. To this end, we introduce a "Physically Adversarial Intelligent Network" (PAIN), wherein self-driving vehicles interact aggressively in the CARLA simulation environment. We train two agents, a protagonist and an adversary, using dueling double deep Q networks (DDDQNs) with prioritized experience replay. The coupled networks alternately seek-to-collide and to avoid collisions such that the "defensive" avoidance algorithm increases the mean-time-to-failure and distance traveled under non-hostile operating conditions. The trained protagonist becomes more resilient to environmental uncertainty and less prone to corner case failures resulting in collisions than the agent trained without an adversary.

Nupur Kumari, Siddarth R., Akash Rupela et al.

We present ShapeVis, a scalable visualization technique for point cloud data inspired from topological data analysis. Our method captures the underlying geometric and topological structure of the data in a compressed graphical representation. Much success has been reported by the data visualization technique Mapper, that discreetly approximates the Reeb graph of a filter function on the data. However, when using standard dimensionality reduction algorithms as the filter function, Mapper suffers from considerable computational cost. This makes it difficult to scale to high-dimensional data. Our proposed technique relies on finding a subset of points called landmarks along the data manifold to construct a weighted witness-graph over it. This graph captures the structural characteristics of the point cloud, and its weights are determined using a Finite Markov Chain. We further compress this graph by applying induced maps from standard community detection algorithms. Using techniques borrowed from manifold tearing, we prune and reinstate edges in the induced graph based on their modularity to summarize the shape of data. We empirically demonstrate how our technique captures the structural characteristics of real and synthetic data sets. Further, we compare our approach with Mapper using various filter functions like t-SNE, UMAP, LargeVis and show that our algorithm scales to millions of data points while preserving the quality of data visualization.

Nikaash Puri, Sukriti Verma, Piyush Gupta et al.

As deep reinforcement learning (RL) is applied to more tasks, there is a need to visualize and understand the behavior of learned agents. Saliency maps explain agent behavior by highlighting the features of the input state that are most relevant for the agent in taking an action. Existing perturbation-based approaches to compute saliency often highlight regions of the input that are not relevant to the action taken by the agent. Our proposed approach, SARFA (Specific and Relevant Feature Attribution), generates more focused saliency maps by balancing two aspects (specificity and relevance) that capture different desiderata of saliency. The first captures the impact of perturbation on the relative expected reward of the action to be explained. The second downweighs irrelevant features that alter the relative expected rewards of actions other than the action to be explained. We compare SARFA with existing approaches on agents trained to play board games (Chess and Go) and Atari games (Breakout, Pong and Space Invaders). We show through illustrative examples (Chess, Atari, Go), human studies (Chess), and automated evaluation methods (Chess) that SARFA generates saliency maps that are more interpretable for humans than existing approaches. For the code release and demo videos, see https://nikaashpuri.github.io/sarfa-saliency/.

Nikaash Puri, Piyush Gupta, Pratiksha Agarwal et al.

Explaining the behavior of a black box machine learning model at the instance level is useful for building trust. However, it is also important to understand how the model behaves globally. Such an understanding provides insight into both the data on which the model was trained and the patterns that it learned. We present here an approach that learns if-then rules to globally explain the behavior of black box machine learning models that have been used to solve classification problems. The approach works by first extracting conditions that were important at the instance level and then evolving rules through a genetic algorithm with an appropriate fitness function. Collectively, these rules represent the patterns followed by the model for decisioning and are useful for understanding its behavior. We demonstrate the validity and usefulness of the approach by interpreting black box models created using publicly available data sets as well as a private digital marketing data set.