Melkior Ornik

Pranay Thangeda, Trevor S. Betz, Michael N. Grussing et al.

Efficient management of infrastructure systems is crucial for economic stability, sustainability, and public safety. However, infrastructure sustainment is challenging due to the vast scale of systems, stochastic deterioration of components, partial observability, and resource constraints. Decision-making strategies that rely solely on human judgment often result in suboptimal decisions over large scales and long horizons. While data-driven approaches like reinforcement learning offer promising solutions, their application has been limited by the lack of suitable simulation environments. We present InfraLib, an open-source modular and extensible framework that enables modeling and analyzing infrastructure management problems with resource constraints as sequential decision-making problems. The framework implements hierarchical, stochastic deterioration models, supports realistic partial observability, and handles practical constraints including cyclical budgets and component unavailability. InfraLib provides standardized environments for benchmarking decision-making approaches, along with tools for expert data collection and policy evaluation. Through case studies on both synthetic benchmarks and real-world road networks, we demonstrate InfraLib's ability to model diverse infrastructure management scenarios while maintaining computational efficiency at scale.

Dantong Ge, Melkior Ornik, Ufuk Topcu

Control of systems operating in unexplored environments is challenging due to lack of complete model knowledge. Additionally, under measurement noises, data collected from onboard sensors are of limited accuracy. This paper considers imperfect state observations in developing a control strategy for systems moving in unknown environments. First, we include hard constraints in the problem for safety concerns. Given the observed states, the robust myopic control approach learns local dynamics, explores all possible trajectories within the observation error bound, and computes the optimal control action using robust optimization. Finally, we validate the method in an OSIRIS-REx-based asteroid landing scenario.

Manav Vora, Pranay Thangeda, Michael N. Grussing et al.

Partially Observable Markov Decision Processes (POMDPs) provide an efficient way to model real-world sequential decision making processes. Motivated by the problem of maintenance and inspection of a group of infrastructure components with independent dynamics, this paper presents an algorithm to find the optimal policy for a multi-component budget-constrained POMDP. We first introduce a budgeted-POMDP model (b-POMDP) which enables us to find the optimal policy for a POMDP while adhering to budget constraints. Next, we prove that the value function or maximal collected reward for a b-POMDP is a concave function of the budget for the finite horizon case. Our second contribution is an algorithm to calculate the optimal policy for a multi-component budget-constrained POMDP by finding the optimal budget split among the individual component POMDPs. The optimal budget split is posed as a welfare maximization problem and the solution is computed by exploiting the concave nature of the value function. We illustrate the effectiveness of the proposed algorithm by proposing a maintenance and inspection policy for a group of real-world infrastructure components with different deterioration dynamics, inspection and maintenance costs. We show that the proposed algorithm vastly outperforms the policy currently used in practice.

Manav Vora, Jonas Liang, Michael N. Grussing et al.

Monotonic Partially Observable Markov Decision Processes (POMDPs), where the system state progressively decreases until a restorative action is performed, can be used to model sequential repair problems effectively. This paper considers the problem of solving budget-constrained multi-component monotonic POMDPs, where a finite budget limits the maximal number of restorative actions. For a large number of components, solving such a POMDP using current methods is computationally intractable due to the exponential growth in the state space with an increasing number of components. To address this challenge, we propose a two-step approach. Since the individual components of a budget-constrained multi-component monotonic POMDP are only connected via the shared budget, we first approximate the optimal budget allocation among these components using an approximation of each component POMDP's optimal value function which is obtained through a random forest model. Subsequently, we introduce an oracle-guided meta-trained Proximal Policy Optimization (PPO) algorithm to solve each of the independent budget-constrained single-component monotonic POMDPs. The oracle policy is obtained by performing value iteration on the corresponding monotonic Markov Decision Process (MDP). This two-step method provides scalability in solving truly massive multi-component monotonic POMDPs. To demonstrate the efficacy of our approach, we consider a real-world maintenance scenario that involves inspection and repair of an administrative building by a team of agents within a maintenance budget. Finally, we perform a computational complexity analysis for a varying number of components to show the scalability of the proposed approach.

Pranay Thangeda, Hoda Helmi, Melkior Ornik

Efficient order fulfillment is vital in the agricultural industry, particularly due to the seasonal nature of seed supply chains. This paper addresses the challenge of optimizing seed orders fulfillment in a centralized warehouse where orders are processed in waves, taking into account the unpredictable arrival of seed stocks and strict order deadlines. We model the wave scheduling problem as a Markov decision process and propose an adaptive hybrid tree search algorithm that combines Monte Carlo tree search with domain-specific knowledge to efficiently navigate the complex, dynamic environment of seed distribution. By leveraging historical data and stochastic modeling, our method enables forecast-informed scheduling decisions that balance immediate requirements with long-term operational efficiency. The key idea is that we can augment Monte Carlo tree search algorithm with problem-specific side information that dynamically reduces the number of candidate actions at each decision step to handle the large state and action spaces that render traditional solution methods computationally intractable. Extensive simulations with realistic parameters, including a diverse range of products, a high volume of orders, and authentic seasonal durations, demonstrate that the proposed approach significantly outperforms existing industry standard methods.

Yifan Zhu, Pranay Thangeda, Erica L Tevere et al.

Autonomous lander missions on extraterrestrial bodies need to sample granular materials while coping with domain shifts, even when sampling strategies are extensively tuned on Earth. To tackle this challenge, this paper studies the few-shot scooping problem and proposes a vision-based adaptive scooping strategy that uses the deep kernel Gaussian process method trained with a novel meta-training strategy to learn online from very limited experience on out-of-distribution target terrains. Our Deep Kernel Calibration with Maximal Deployment Gaps (kCMD) strategy explicitly trains a deep kernel model to adapt to large domain shifts by creating simulated maximal deployment gaps from an offline training dataset and training models to overcome these deployment gaps during training. Employed in a Bayesian Optimization sequential decision-making framework, the proposed method allows the robot to perform high-quality scooping actions on out-of-distribution terrains after a few attempts, significantly outperforming non-adaptive methods proposed in the excavation literature as well as other state-of-the-art meta-learning methods. The proposed method also demonstrates zero-shot transfer capability, successfully adapting to the NASA OWLAT platform, which serves as a state-of-the-art simulator for potential future planetary missions. These results demonstrate the potential of training deep models with simulated deployment gaps for more generalizable meta-learning in high-capacity models. Furthermore, they highlight the promise of our method in autonomous lander sampling missions by enabling landers to overcome the deployment gap between Earth and extraterrestrial bodies.

Ratnangshu Das, Ram Padmanabhan, Melkior Ornik et al.

In environments with uncertainties or undesirable influences, control systems can require additional energy to achieve their task while remaining resilient to these influences. In this paper, we present an energetic resilience metric that quantifies the maximal additional energy used by a system under undesired effects, while satisfying complex specifications encoded through temporal logic. We prove that this metric satisfies properties that enable its computation even for compositions of these specifications, thus allowing considerations of sequential reachability and safety tasks. For specifications related to finite-horizon reachability and safety, we describe how synthesizing a control input and computing this metric reduces to solving efficient quadratic programs. Two case studies on a fighter-jet model and a planar mobile robot illustrate how the synthesized control inputs satisfy given specifications despite undesired and potentially adversarial effects. Further, we demonstrate how the energetic resilience metric varies with the initial state as well as the magnitude of undesired effects.

Neeloy Chakraborty, Melkior Ornik, Katherine Driggs-Campbell

Autonomous systems are soon to be ubiquitous, spanning manufacturing, agriculture, healthcare, entertainment, and other industries. Most of these systems are developed with modular sub-components for decision-making, planning, and control that may be hand-engineered or learning-based. While these approaches perform well under the situations they were specifically designed for, they can perform especially poorly in out-of-distribution scenarios that will undoubtedly arise at test-time. The rise of foundation models trained on multiple tasks with impressively large datasets has led researchers to believe that these models may provide "common sense" reasoning that existing planners are missing, bridging the gap between algorithm development and deployment. While researchers have shown promising results in deploying foundation models to decision-making tasks, these models are known to hallucinate and generate decisions that may sound reasonable, but are in fact poor. We argue there is a need to step back and simultaneously design systems that can quantify the certainty of a model's decision, and detect when it may be hallucinating. In this work, we discuss the current use cases of foundation models for decision-making tasks, provide a general definition for hallucinations with examples, discuss existing approaches to hallucination detection and mitigation with a focus on decision problems, present guidelines, and explore areas for further research in this exciting field.

Gokul Puthumanaillam, Manav Vora, Pranay Thangeda et al.

This paper examines the challenges associated with achieving life-long superalignment in AI systems, particularly large language models (LLMs). Superalignment is a theoretical framework that aspires to ensure that superintelligent AI systems act in accordance with human values and goals. Despite its promising vision, we argue that achieving superalignment requires substantial changes in the current LLM architectures due to their inherent limitations in comprehending and adapting to the dynamic nature of these human ethics and evolving global scenarios. We dissect the challenges of encoding an ever-changing spectrum of human values into LLMs, highlighting the discrepancies between static AI models and the dynamic nature of human societies. To illustrate these challenges, we analyze two distinct examples: one demonstrates a qualitative shift in human values, while the other presents a quantifiable change. Through these examples, we illustrate how LLMs, constrained by their training data, fail to align with contemporary human values and scenarios. The paper concludes by exploring potential strategies to address and possibly mitigate these alignment discrepancies, suggesting a path forward in the pursuit of more adaptable and responsive AI systems.

Gokul Puthumanaillam, Xiangyu Liu, Negar Mehr et al.

Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments. Environmental variability over time can significantly impact the system's optimal decision making strategy for mission completion. To model such environments, our work combines the previous notion of Time-Varying Markov Decision Processes (TVMDP) with partial observability and introduces Time-Varying Partially Observable Markov Decision Processes (TV-POMDP). We propose a two-pronged approach to accurately estimate and plan within the TV-POMDP: 1) Memory Prioritized State Estimation (MPSE), which leverages weighted memory to provide more accurate time-varying transition estimates; and 2) an MPSE-integrated planning strategy that optimizes long-term rewards while accounting for temporal constraint. We validate the proposed framework and algorithms using simulations and hardware, with robots exploring a partially observable, time-varying environments. Our results demonstrate superior performance over standard methods, highlighting the framework's effectiveness in stochastic, uncertain, time-varying domains.

Gokul Puthumanaillam, Manav Vora, Melkior Ornik

Optimal decision-making for trajectory tracking in partially observable, stochastic environments where the number of active localization updates -- the process by which the agent obtains its true state information from the sensors -- are limited, presents a significant challenge. Traditional methods often struggle to balance resource conservation, accurate state estimation and precise tracking, resulting in suboptimal performance. This problem is particularly pronounced in environments with large action spaces, where the need for frequent, accurate state data is paramount, yet the capacity for active localization updates is restricted by external limitations. This paper introduces ComTraQ-MPC, a novel framework that combines Deep Q-Networks (DQN) and Model Predictive Control (MPC) to optimize trajectory tracking with constrained active localization updates. The meta-trained DQN ensures adaptive active localization scheduling, while the MPC leverages available state information to improve tracking. The central contribution of this work is their reciprocal interaction: DQN's update decisions inform MPC's control strategy, and MPC's outcomes refine DQN's learning, creating a cohesive, adaptive system. Empirical evaluations in simulated and real-world settings demonstrate that ComTraQ-MPC significantly enhances operational efficiency and accuracy, providing a generalizable and approximately optimal solution for trajectory tracking in complex partially observable environments.

Gokul Puthumanaillam, Paulo Padrao, Jose Fuentes et al.

Robots navigating complex environments must manage uncertainty from sensor noise, environmental changes, and incomplete information, with different tasks requiring varying levels of precision in different areas. For example, precise localization may be crucial near obstacles but less critical in open spaces. We present GUIDE (Generalized Uncertainty Integration for Decision-Making and Execution), a framework that integrates these task-specific requirements into navigation policies via Task-Specific Uncertainty Maps (TSUMs). By assigning acceptable uncertainty levels to different locations, TSUMs enable robots to adapt uncertainty management based on context. When combined with reinforcement learning, GUIDE learns policies that balance task completion and uncertainty management without extensive reward engineering. Real-world tests show significant performance gains over methods lacking task-specific uncertainty awareness.

Gokul Puthumanaillam, Jae Hyuk Song, Nurzhan Yesmagambet et al.

Autonomous agents operating in adversarial scenarios face a fundamental challenge: while they may know their adversaries' high-level objectives, such as reaching specific destinations within time constraints, the exact policies these adversaries will employ remain unknown. Traditional approaches address this challenge by treating the adversary's state as a partially observable element, leading to a formulation as a Partially Observable Markov Decision Process (POMDP). However, the induced belief-space dynamics in a POMDP require knowledge of the system's transition dynamics, which, in this case, depend on the adversary's unknown policy. Our key observation is that while an adversary's exact policy is unknown, their behavior is necessarily constrained by their mission objectives and the physical environment, allowing us to characterize the space of possible behaviors without assuming specific policies. In this paper, we develop Task-Aware Behavior Fields (TAB-Fields), a representation that captures adversary state distributions over time by computing the most unbiased probability distribution consistent with known constraints. We construct TAB-Fields by solving a constrained optimization problem that minimizes additional assumptions about adversary behavior beyond mission and environmental requirements. We integrate TAB-Fields with standard planning algorithms by introducing TAB-conditioned POMCP, an adaptation of Partially Observable Monte Carlo Planning. Through experiments in simulation with underwater robots and hardware implementations with ground robots, we demonstrate that our approach achieves superior performance compared to baselines that either assume specific adversary policies or neglect mission constraints altogether. Evaluation videos and code are available at https://tab-fields.github.io.

Gokul Puthumanaillam, Paulo Padrao, Jose Fuentes et al.

Autonomous vehicles performing navigation tasks in complex environments face significant challenges due to uncertainty in state estimation. In many scenarios, such as stealth operations or resource-constrained settings, accessing high-precision localization comes at a significant cost, forcing robots to rely primarily on less precise state estimates. Our key observation is that different tasks require varying levels of precision in different regions: a robot navigating a crowded space might need precise localization near obstacles but can operate effectively with less precision elsewhere. In this paper, we present a planning method for integrating task-specific uncertainty requirements directly into navigation policies. We introduce Task-Specific Uncertainty Maps (TSUMs), which abstract the acceptable levels of state estimation uncertainty across different regions. TSUMs align task requirements and environmental features using a shared representation space, generated via a domain-adapted encoder. Using TSUMs, we propose Generalized Uncertainty Integration for Decision-Making and Execution (GUIDE), a policy conditioning framework that incorporates these uncertainty requirements into robot decision-making. We find that TSUMs provide an effective way to abstract task-specific uncertainty requirements, and conditioning policies on TSUMs enables the robot to reason about the context-dependent value of certainty and adapt its behavior accordingly. We show how integrating GUIDE into reinforcement learning frameworks allows the agent to learn navigation policies that effectively balance task completion and uncertainty management without explicit reward engineering. We evaluate GUIDE on various real-world robotic navigation tasks and find that it demonstrates significant improvement in task completion rates compared to baseline methods that do not explicitly consider task-specific uncertainty.

Neeloy Chakraborty, John Pohovey, Melkior Ornik et al.

Large language models (LLMs) have recently demonstrated success in generalizing across decision-making tasks including planning, control, and prediction, but their tendency to hallucinate unsafe and undesired outputs poses risks. We argue that detecting such failures is necessary, especially in safety-critical scenarios. Existing methods for black-box models often detect hallucinations by identifying inconsistencies across multiple samples. Many of these approaches typically introduce prompt perturbations like randomizing detail order or generating adversarial inputs, with the intuition that a confident model should produce stable outputs. We first perform a manual case study showing that other forms of perturbations (e.g., adding noise, removing sensor details) cause LLMs to hallucinate in a multi-agent driving environment. We then propose a novel method for efficiently searching the space of prompt perturbations using adaptive stress testing (AST) with Monte-Carlo tree search (MCTS). Our AST formulation enables discovery of scenarios and prompts that cause language models to act with high uncertainty or even crash. By generating MCTS prompt perturbation trees across diverse scenarios, we show through extensive experiments that offline analyses can be used at runtime to automatically generate prompts that influence model uncertainty, and to inform real-time trust assessments of an LLM. We further characterize LLMs deployed as planners in a single-agent lunar lander environment and in a multi-agent robot crowd navigation simulation. Overall, ours is one of the first hallucination intervention algorithms to pave a path towards rigorous characterization of black-box LLM planners.

Manav Vora, Ilan Shomorony, Melkior Ornik

We study capacity- and budget-constrained multi-agent MDPs (CB-MA-MDPs), a class that captures many maintenance and scheduling tasks in which each agent can irreversibly fail and a planner must decide (i) when to apply a restorative action and (ii) which subset of agents to treat in parallel. The global budget limits the total number of restorations, while the capacity constraint bounds the number of simultaneous actions, turning naïve dynamic programming into a combinatorial search that scales exponentially with the number of agents. We propose a two-stage solution that remains tractable for large systems. First, a Linear Sum Assignment Problem (LSAP)-based grouping partitions the agents into r disjoint sets (r = capacity) that maximise diversity in expected time-to-failure, allocating budget to each set proportionally. Second, a meta-trained PPO policy solves each sub-MDP, leveraging transfer across groups to converge rapidly. To validate our approach, we apply it to the problem of scheduling repairs for a large team of industrial robots, constrained by a limited number of repair technicians and a total repair budget. Our results demonstrate that the proposed method outperforms baseline approaches in terms of maximizing the average uptime of the robot team, particularly for large team sizes. Lastly, we confirm the scalability of our approach through a computational complexity analysis across varying numbers of robots and repair technicians.

František Blahoudek, Petr Novotný, Melkior Ornik et al.

We consider qualitative strategy synthesis for the formalism called consumption Markov decision processes. This formalism can model dynamics of an agents that operates under resource constraints in a stochastic environment. The presented algorithms work in time polynomial with respect to the representation of the model and they synthesize strategies ensuring that a given set of goal states will be reached (once or infinitely many times) with probability 1 without resource exhaustion. In particular, when the amount of resource becomes too low to safely continue in the mission, the strategy changes course of the agent towards one of a designated set of reload states where the agent replenishes the resource to full capacity; with sufficient amount of resource, the agent attempts to fulfill the mission again. We also present two heuristics that attempt to reduce expected time that the agent needs to fulfill the given mission, a parameter important in practical planning. The presented algorithms were implemented and numerical examples demonstrate (i) the effectiveness (in terms of computation time) of the planning approach based on consumption Markov decision processes and (ii) the positive impact of the two heuristics on planning in a realistic example.

Melkior Ornik, Ufuk Topcu

This paper proposes a formal approach to online learning and planning for agents operating in a priori unknown, time-varying environments. The proposed method computes the maximally likely model of the environment, given the observations about the environment made by an agent earlier in the system run and assuming knowledge of a bound on the maximal rate of change of system dynamics. Such an approach generalizes the estimation method commonly used in learning algorithms for unknown Markov decision processes with time-invariant transition probabilities, but is also able to quickly and correctly identify the system dynamics following a change. Based on the proposed method, we generalize the exploration bonuses used in learning for time-invariant Markov decision processes by introducing a notion of uncertainty in a learned time-varying model, and develop a control policy for time-varying Markov decision processes based on the exploitation and exploration trade-off. We demonstrate the proposed methods on four numerical examples: a patrolling task with a change in system dynamics, a two-state MDP with periodically changing outcomes of actions, a wind flow estimation task, and a multi-armed bandit problem with periodically changing probabilities of different rewards.

Melkior Ornik, Ufuk Topcu

In this paper, we consider an adversarial scenario where one agent seeks to achieve an objective and its adversary seeks to learn the agent's intentions and prevent the agent from achieving its objective. The agent has an incentive to try to deceive the adversary about its intentions, while at the same time working to achieve its objective. The primary contribution of this paper is to introduce a mathematically rigorous framework for the notion of deception within the context of optimal control. The central notion introduced in the paper is that of a belief-induced reward: a reward dependent not only on the agent's state and action, but also adversary's beliefs. Design of an optimal deceptive strategy then becomes a question of optimal control design on the product of the agent's state space and the adversary's belief space. The proposed framework allows for deception to be defined in an arbitrary control system endowed with a reward function, as well as with additional specifications limiting the agent's control policy. In addition to defining deception, we discuss design of optimally deceptive strategies under uncertainties in agent's knowledge about the adversary's learning process. In the latter part of the paper, we focus on a setting where the agent's behavior is governed by a Markov decision process, and show that the design of optimally deceptive strategies under lack of knowledge about the adversary naturally reduces to previously discussed problems in control design on partially observable or uncertain Markov decision processes. Finally, we present two examples of deceptive strategies: a "cops and robbers" scenario and an example where an agent may use camouflage while moving. We show that optimally deceptive strategies in such examples follow the intuitive idea of how to deceive an adversary in the above settings.

Melkior Ornik, Arie Israel, Ufuk Topcu

This paper focuses on developing a strategy for control of systems whose dynamics are almost entirely unknown. This situation arises naturally in a scenario where a system undergoes a critical failure. In that case, it is imperative to retain the ability to satisfy basic control objectives in order to avert an imminent catastrophe. A prime example of such an objective is the reach-avoid problem, where a system needs to move to a certain state in a constrained state space. To deal with limitations on our knowledge of system dynamics, we develop a theory of myopic control. The primary goal of myopic control is to, at any given time, optimize the current direction of the system trajectory, given solely the information obtained about the system until that time. We propose an algorithm that uses small perturbations in the control effort to learn local dynamics while simultaneously ensuring that the system moves in a direction that appears to be nearly optimal, and provide hard bounds for its suboptimality. We additionally verify the usefulness of the algorithm on a simulation of a damaged aircraft seeking to avoid a crash, as well as on an example of a Van der Pol oscillator.