paper-with-me

홈 › Papers

Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation

2023-03-02 · Orin Levy, Alon Cohen, Asaf Cassel, Yishay Mansour

We present the OMG-CMDP! algorithm for regret minimization in adversarial Contextual MDPs. The algorithm operates under the minimal assumptions of realizable function class and access to online least squares and log loss regression oracles. Our algorithm is efficient (assuming efficient online regression oracles), simple and robust to approximation errors. It enjoys an $\widetilde{O}(H^{2.5} \sqrt{ T|S||A| ( \mathcal{R}(\mathcal{O}) + H \log(\delta^{-1}) )})$ regret guarantee, with $T$ being the number of episodes, $S$ the state space, $A$ the action space, $H$ the horizon and $\mathcal{R}(\mathcal{O}) = \mathcal{R}(\mathcal{O}_{\mathrm{sq}}^\mathcal{F}) + \mathcal{R}(\mathcal{O}_{\mathrm{log}}^\mathcal{P})$ is the sum of the regression oracles' regret, used to approximate the context-dependent rewards and dynamics, respectively. To the best of our knowledge, our algorithm is the first efficient rate optimal regret minimization algorithm for adversarial CMDPs that operates under the minimal standard assumption of online function approximation.

📄 PDF Abstract BibTeX arXiv:2303.01464

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation

2026-02-14 · Orin Levy, Aviv Rosenberg, Alon Cohen, Yishay Mansour arxiv

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability reg…

Dynamic Regret of Adversarial Linear Mixture MDPs

2023-09-21 · NeurIPS 2023 11

We study reinforcement learning in episodic inhomogeneous MDPs with adversarial full-information rewards and the unknown transition kernel. We consider the linear mixture MDPs whose transition kernel is a linear mixture …

Reinforcement Learning from Adversarial Preferences in Tabular MDPs

2025-07-15 · Taira Tsuchiya, Shinji Ito, Haipeng Luo arxiv

We introduce a new framework of episodic tabular Markov decision processes (MDPs) with adversarial preferences, which we refer to as preference-based MDPs (PbMDPs). Unlike standard episodic MDPs with adversarial losses, …

Reinforcement Learning

Scale-free Adversarial Reinforcement Learning

2024-03-01 · Mingyu Chen, Xuezhou Zhang

This paper initiates the study of scale-free learning in Markov Decision Processes (MDPs), where the scale of rewards/losses is unknown to the learner. We design a generic algorithmic framework, \underline{S}cale \underl…

reinforcement-learningReinforcement Learning

Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards

2026-03-29 · Kihyun Yu, Seoungbin Bae, Dabeen Lee arxiv

We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes (CMDPs) with adversarial rewards under full-information feedback and an unknown transition kernel. We propose a …

Reinforcement Learning