4 papers
Provably Efficient Sample Complexity for Robust CMDP
Sourav Ganguly, Arnob Ghosh
We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal mo…
Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees
Zuyuan Zhang, Arnob Ghosh, Tian Lan
Making decisions with respect to just the expected returns in Monte Carlo Tree Search (MCTS) cannot account for the potential range of high-risk, adverse outcomes associated with a…
Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
Amirhossein Roknilamouki, Arnob Ghosh, Ming Shi +3
In Reinforcement Learning (RL), tasks with instantaneous hard constraints present significant challenges, particularly when the decision space is non-convex or non-star-convex. Thi…
Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno +5
We study the reinforcement learning (RL) problem in a constrained Markov decision process (CMDP), where an agent explores the environment to maximize the expected cumulative reward…