Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation
원문 초록
For a risk-averse finite-horizon Markov Decision Process, we introduce a special class of Markov coherent risk measures, called mini-batch measures. We also define the class of multipattern risk-averse problems that reduce to linear MDPs in the risk-neutral case. We use both concepts in a feature-based $Q$-learning method with multipattern $Q$-factor approximation and we prove a high-probability regret bound of $\widetilde{\mathcal{O}}\big(d^{3/2}HN^{H-1}\sqrt{K}\big)$, where $d$ is the number of features, $H$ is the horizon, $N\ge2$ is the mini-batch size, $K$ is the number of episodes, and $\widetilde{\mathcal{O}}$ hides logarithmic factors. We also propose an economical version of the $Q$-learning method that streamlines the policy evaluation (backward) step. The theoretical results are illustrated on a stochastic assignment problem and a short-horizon multi-armed bandit problem.
제출 이력
확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.
- arXiv:2605.00654v2제출 시각 미확인
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
공통 태그로 연결된 공개 논문이 아직 없습니다.
토론
이 논문과 연결된 포럼 글이 아직 없습니다.