LGSep 27, 2023

Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need

arXiv:2309.15737v1h-index: 49
Originality Highly original
AI Analysis

This work addresses efficient exploration in constrained reinforcement learning, providing a provably optimal solution for communicating CMDPs in the infinite-horizon undiscounted setting.

The paper tackles the problem of learning in constrained Markov decision processes (CMDPs) by proposing a new posterior sampling algorithm, achieving a near-optimal Bayesian regret bound of ˜O(HS√AT) and outperforming existing algorithms empirically.

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous empirically compared to the existing algorithms. Our main theoretical result is a Bayesian regret bound for each cost component of \tilde{O} (HS \sqrt{AT}) for any communicating CMDP with S states, A actions, and bound on the hitting time H. This regret bound matches the lower bound in order of time horizon T and is the best-known regret bound for communicating CMDPs in the infinite-horizon undiscounted setting. Empirical results show that, despite its simplicity, our posterior sampling algorithm outperforms the existing algorithms for constrained reinforcement learning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes