Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
원문 초록
This paper studies the safe reinforcement learning problem formulated as an episodic finite-horizon tabular constrained Markov decision process with an unknown transition kernel and stochastic reward and cost functions. We propose a model-based algorithm based on novel cost and reward function estimators that provide tighter cost pessimism and reward optimism. While guaranteeing no constraint violation in every episode, our algorithm achieves a regret upper bound of $\widetilde{\mathcal{O}}((\bar C - \bar C_b)^{-1}H^{2.5} S\sqrt{AK})$ where $\bar C$ is the cost budget for an episode, $\bar C_b$ is the expected cost under a safe baseline policy over an episode, $H$ is the horizon, and $S$, $A$ and $K$ are the number of states, actions, and episodes, respectively. This improves upon the best-known regret upper bound, and when $\bar C- \bar C_b=\Omega(H)$, it nearly matches the regret lower bound of $\Omega(H^{1.5}\sqrt{SAK})$. We deduce our cost and reward function estimators via a Bellman-type law of total variance to obtain tight bounds on the expected sum of the variances of value function estimates. This leads to a tighter dependence on the horizon in the function estimators. We also present numerical results to demonstrate the computational effectiveness of our proposed framework.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints
Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learning
Risk-Averse Reinforcement Learning: An Optimal Transport Perspective on Temporal Difference Learning
Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning
Offline Safe Reinforcement Learning Using Trajectory Classification
Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.