1 citations · 1 across the 13 of their papers we have counts for
15 papers
SafePG: Safe and Globally Optimal Reinforcement Learning with Hard Constraints
Vipul K. Sharma, Wesley A. Suttle, S. Sivaranjani
We present an optimal and convergent model-free policy gradient (PG) reinforcement learning (RL) framework for controlling nonlinear dynamical systems under hard safety constraints…
Efficiently Solving Mixed-Hierarchy Games with Quasi-Policy Approximations
Hamzah Khan, Dong Ho Lee, Jingqi Li +5
Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. While game theory provides a principled fr…
Deceptive Exploration in Multi-armed Bandits
I. Arda Vurankaya, Mustafa O. Karabag, Wesley A. Suttle +3
We consider a multi-armed bandit setting in which each arm has a public and a private reward distribution. An observer expects an agent to follow Thompson Sampling according to the…
IMAS: Joint Agent Selection and Information-Theoretic Coordinated Perception In Dec-POMDPs
Chongyang Shi, Wesley A. Suttle, Michael Dorothy +1
We study the problem of jointly selecting sensing agents and synthesizing decentralized active perception policies for the chosen subset of agents within a Decentralized Partially…
Signal attenuation enables scalable decentralized multi-agent reinforcement learning over networks
Wesley A Suttle, Vipul K Sharma, Brian M Sadler
Multi-agent reinforcement learning (MARL) methods typically require that agents enjoy global state observability, preventing development of decentralized algorithms and limiting sc…
Value of Information-based Deceptive Path Planning Under Adversarial Interventions
Wesley A. Suttle, Jesse Milzman, Mustafa O. Karabag +2
Existing methods for deceptive path planning (DPP) address the problem of designing paths that conceal their true goal from a passive, external observer. Such methods do not apply…
Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning
Wesley A. Suttle, Aamodh Suresh, Carlos Nieto-Granda
Entropy-based objectives are widely used to perform state space exploration in reinforcement learning (RL) and dataset generation for offline RL. Behavioral entropy (BE), a rigorou…
Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach
Utsav Singh, Souradip Chakraborty, Wesley A. Suttle +6
Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods face two fundament…
Code Comprehension then Auditing for Unsupervised LLM Evaluation
Bhrij Patel, Souradip Chakraborty, Mengdi Wang +2
Large Language Models (LLMs) for unsupervised code correctness evaluation have recently gained attention because they can judge if code runs as intended without requiring reference…
DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning
Utsav Singh, Souradip Chakraborty, Wesley A. Suttle +3
Learning control policies to perform complex robotics tasks from human preference data presents significant challenges. On the one hand, the complexity of such tasks typically requ…
PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
Utsav Singh, Wesley A. Suttle, Brian M. Sadler +2
In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based…
Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
Wesley A. Suttle, Vipul K. Sharma, Krishna C. Kosaraju +4
We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of co…
Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
Bhrij Patel, Wesley A. Suttle, Alec Koppel +4
In the context of average-reward reinforcement learning, the requirement for oracle knowledge of the mixing time, a measure of the duration a Markov chain under a fixed policy need…
Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks
Michael Y. Fatemi, Wesley A. Suttle, Brian M. Sadler
Deceptive path planning (DPP) is the problem of designing a path that hides its true goal from an outside observer. Existing methods for DPP rely on unrealistic assumptions, such a…
Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic
Wesley A. Suttle, Amrit Singh Bedi, Bhrij Patel +3
Many existing reinforcement learning (RL) methods employ stochastic gradient iteration on the back end, whose stability hinges upon a hypothesis that the data-generating process mi…