Abstract:Many reinforcement learning (RL) algorithms require large amounts of data, prohibiting their use in applications where frequent interactions with operational systems are infeasible, or high-fidelity simulations are expensive or unavailable. Meanwhile, low-fidelity simulators--such as reduced-order models, heuristic reward functions, or generative world models--can cheaply provide useful data for RL training, even if they are too coarse for direct sim-to-real transfer. We propose multi-fidelity policy gradients (MFPGs), an RL framework that mixes a small amount of data from the target environment with a large volume of low-fidelity simulation data to form unbiased, reduced-variance estimators (control variates) for on-policy policy gradients. We instantiate the framework by developing multi-fidelity variants of two policy gradient algorithms: REINFORCE and proximal policy optimization. Experimental results across a suite of simulated robotics benchmark problems demonstrate that when target-environment samples are limited, MFPG achieves up to 3.9x higher reward and improves training stability when compared to baselines that only use high-fidelity data. Moreover, even when the baselines are given more high-fidelity samples--up to 10x as many interactions with the target environment--MFPG continues to match or outperform them. Finally, we observe that MFPG is capable of training effective policies even when the low-fidelity environment is drastically different from the target environment. MFPG thus not only offers a novel paradigm for efficient sim-to-real transfer but also provides a principled approach to managing the trade-off between policy performance and data collection costs.
Abstract:Large Language Models (LLMs) are increasingly used for planning tasks, offering unique capabilities not found in classical planners such as generating explanations and iterative refinement. However, trust--a critical factor in the adoption of planning systems--remains underexplored in the context of LLM-based planning tasks. This study bridges this gap by comparing human trust in LLM-based planners with classical planners through a user study in a Planning Domain Definition Language (PDDL) domain. Combining subjective measures, such as trust questionnaires, with objective metrics like evaluation accuracy, our findings reveal that correctness is the primary driver of trust and performance. Explanations provided by the LLM improved evaluation accuracy but had limited impact on trust, while plan refinement showed potential for increasing trust without significantly enhancing evaluation accuracy.
Abstract:In strategic multi-agent sequential interactions, detecting dynamic coalition structures is crucial for understanding how self-interested agents coordinate to influence outcomes. However, natural-language-based interactions introduce unique challenges to coalition detection due to ambiguity over intents and difficulty in modeling players' subjective perspectives. We propose a new method that leverages recent advancements in large language models and game theory to predict dynamic multilateral coalition formation in Diplomacy, a strategic multi-agent game where agents negotiate coalitions using natural language. The method consists of two stages. The first stage extracts the set of agreements discussed by two agents in their private dialogue, by combining a parsing-based filtering function with a fine-tuned language model trained to predict player intents. In the second stage, we define a new metric using the concept of subjective rationalizability from hypergame theory to evaluate the expected value of an agreement for each player. We then compute this metric for each agreement identified in the first stage by assessing the strategic value of the agreement for both players and taking into account the subjective belief of one player that the second player would honor the agreement. We demonstrate that our method effectively detects potential coalition structures in online Diplomacy gameplay by assigning high values to agreements likely to be honored and low values to those likely to be violated. The proposed method provides foundational insights into coalition formation in multi-agent environments with language-based negotiation and offers key directions for future research on the analysis of complex natural language-based interactions between agents.
Abstract:Human-robot cooperative navigation is challenging in environments with incomplete information. We introduce CoNav-Maze, a simulated robotics environment where a robot navigates using local perception while a human operator provides guidance based on an inaccurate map. The robot can share its camera views to improve the operator's understanding of the environment. To enable efficient human-robot cooperation, we propose Information Gain Monte Carlo Tree Search (IG-MCTS), an online planning algorithm that balances autonomous movement and informative communication. Central to IG-MCTS is a neural human perception dynamics model that estimates how humans distill information from robot communications. We collect a dataset through a crowdsourced mapping task in CoNav-Maze and train this model using a fully convolutional architecture with data augmentation. User studies show that IG-MCTS outperforms teleoperation and instruction-following baselines, achieving comparable task performance with significantly less communication and lower human cognitive load, as evidenced by eye-tracking metrics.
Abstract:Large language model-based (LLM-based) agents have become common in settings that include non-cooperative parties. In such settings, agents' decision-making needs to conceal information from their adversaries, reveal information to their cooperators, and infer information to identify the other agents' characteristics. To investigate whether LLMs have these information control and decision-making capabilities, we make LLM agents play the language-based hidden-identity game, The Chameleon. In the game, a group of non-chameleon agents who do not know each other aim to identify the chameleon agent without revealing a secret. The game requires the aforementioned information control capabilities both as a chameleon and a non-chameleon. The empirical results show that while non-chameleon LLM agents identify the chameleon, they fail to conceal the secret from the chameleon, and their winning probability is far from the levels of even trivial strategies. To formally explain this behavior, we give a theoretical analysis for a spectrum of strategies, from concealing to revealing, and provide bounds on the non-chameleons' winning probability. Based on the empirical results and theoretical analysis of different strategies, we deduce that LLM-based non-chameleon agents reveal excessive information to agents of unknown identities. Our results point to a weakness of contemporary LLMs, including GPT-4, GPT-4o, Gemini 1.5, and Claude 3.5 Sonnet, in strategic interactions.
Abstract:Autonomous systems are increasingly expected to operate in the presence of adversaries, though an adversary may infer sensitive information simply by observing a system, without even needing to interact with it. Therefore, in this work we present a deceptive decision-making framework that not only conceals sensitive information, but in fact actively misleads adversaries about it. We model autonomous systems as Markov decision processes, and we consider adversaries that attempt to infer their reward functions using inverse reinforcement learning. To counter such efforts, we present two regularization strategies for policy synthesis problems that actively deceive an adversary about a system's underlying rewards. The first form of deception is ``diversionary'', and it leads an adversary to draw any false conclusion about what the system's reward function is. The second form of deception is ``targeted'', and it leads an adversary to draw a specific false conclusion about what the system's reward function is. We then show how each form of deception can be implemented in policy optimization problems, and we analytically bound the loss in total accumulated reward that is induced by deception. Next, we evaluate these developments in a multi-agent sequential decision-making problem with one real agent and multiple decoys. We show that diversionary deception can cause the adversary to believe that the most important agent is the least important, while attaining a total accumulated reward that is $98.83\%$ of its optimal, non-deceptive value. Similarly, we show that targeted deception can make any decoy appear to be the most important agent, while still attaining a total accumulated reward that is $99.25\%$ of its optimal, non-deceptive value.
Abstract:A central challenge in transfer learning is designing algorithms that can quickly adapt and generalize to new tasks without retraining. Yet, the conditions of when and how algorithms can effectively transfer to new tasks is poorly characterized. We introduce a geometric characterization of transfer in Hilbert spaces and define three types of inductive transfer: interpolation within the convex hull, extrapolation to the linear span, and extrapolation outside the span. We propose a method grounded in the theory of function encoders to achieve all three types of transfer. Specifically, we introduce a novel training scheme for function encoders using least-squares optimization, prove a universal approximation theorem for function encoders, and provide a comprehensive comparison with existing approaches such as transformers and meta-learning on four diverse benchmarks. Our experiments demonstrate that the function encoder outperforms state-of-the-art methods on four benchmark tasks and on all three types of transfer.
Abstract:Urban air mobility (UAM) is a transformative system that operates various small aerial vehicles in urban environments to reshape urban transportation. However, integrating UAM into existing urban environments presents a variety of complex challenges. Recent analyses of UAM's operational constraints highlight aircraft noise and system safety as key hurdles to UAM system implementation. Future UAM air traffic management schemes must ensure that the system is both quiet and safe. We propose a multi-agent reinforcement learning approach to manage UAM traffic, aiming at both vertical separation assurance and noise mitigation. Through extensive training, the reinforcement learning agent learns to balance the two primary objectives by employing altitude adjustments in a multi-layer UAM network. The results reveal the tradeoffs among noise impact, traffic congestion, and separation. Overall, our findings demonstrate the potential of reinforcement learning in mitigating UAM's noise impact while maintaining safe separation using altitude adjustments
Abstract:We develop compositional learning algorithms for coupled dynamical systems. While deep learning has proven effective at modeling complex relationships from data, compositional couplings between system components typically introduce algebraic constraints on state variables, posing challenges to many existing data-driven approaches to modeling dynamical systems. Towards developing deep learning models for constrained dynamical systems, we introduce neural port-Hamiltonian differential algebraic equations (N-PHDAEs), which use neural networks to parametrize unknown terms in both the differential and algebraic components of a port-Hamiltonian DAE. To train these models, we propose an algorithm that uses automatic differentiation to perform index reduction, automatically transforming the neural DAE into an equivalent system of neural ordinary differential equations (N-ODEs), for which established model inference and backpropagation methods exist. The proposed compositional modeling framework and learning algorithms may be applied broadly to learn control-oriented models of dynamical systems in a variety of application areas, however, in this work, we focus on their application to the modeling of electrical networks. Experiments simulating the dynamics of nonlinear circuits exemplify the benefits of our approach: the proposed N-PHDAE model achieves an order of magnitude improvement in prediction accuracy and constraint satisfaction when compared to a baseline N-ODE over long prediction time horizons. We also validate the compositional capabilities of our approach through experiments on a simulated D.C. microgrid: we train individual N-PHDAE models for separate grid components, before coupling them to accurately predict the behavior of larger-scale networks.
Abstract:Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discovering sequences of actions that lead to a non-zero reward becomes exponentially more difficult as the task horizon increases. Manually shaping rewards can accelerate learning for a fixed task, but it is an arduous process that must be repeated for each new environment. We introduce a systematic reward-shaping framework that distills the information contained in 1) a task-agnostic prior data set and 2) a small number of task-specific expert demonstrations, and then uses these priors to synthesize dense dynamics-aware rewards for the given task. This supervision substantially accelerates learning in our experiments, and we provide analysis demonstrating how the approach can effectively guide online learning agents to faraway goals.