2 papers
stat.ML2024
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning
Jia Wan, Sean R. Sinclair, Devavrat Shah +1
We study a structured class of Markov Decision Processes, known as Exo-MDPs, in which the state space is partitioned into exogenous and endogenous components. Exogenous states evol…
cs.LG2024
Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
Yaqi Duan, Martin J. Wainwright
We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-li…