paper-with-me

Papers

Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited

2020-10-07 · Omar Darwiche Domingues, Pierre Ménard, Emilie Kaufmann, Michal Valko

In this paper, we propose new problem-independent lower bounds on the sample complexity and regret in episodic MDPs, with a particular focus on the non-stationary case in which the transition kernel is allowed to change in each stage of the episode. Our main contribution is a novel lower bound of $\Omega((H^3SA/\epsilon^2)\log(1/\delta))$ on the sample complexity of an $(\varepsilon,\delta)$-PAC algorithm for best policy identification in a non-stationary MDP. This lower bound relies on a construction of "hard MDPs" which is different from the ones previously used in the literature. Using this same class of MDPs, we also provide a rigorous proof of the $\Omega(\sqrt{H^3SAT})$ regret bound for non-stationary MDPs. Finally, we discuss connections to PAC-MDP lower bounds.

📄 PDF Abstract BibTeX arXiv:2010.03531

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees

2026-04-17 · Argyrios Gerogiannis, Yu-Han Huang, Venugopal V. Veeravalli arxiv

We study model-free reinforcement learning (RL) in non-stationary finite-horizon episodic Markov decision processes (MDPs) without prior knowledge of the non-stationarity. We focus on the piecewise stationary (PS) settin…

Reinforcement Learning

Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs

2022-03-17 · Andrea Tirinzoni, Aymen Al-Marjani, Emilie Kaufmann

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$. While minimax optimal algorithms exist for this problem, its…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

2020-06-24 · NeurIPS 2020 12 · Yi Tian, Jian Qian, Suvrit Sra

We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components. Assuming the factorization is known, we propose…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Nonstationary Reinforcement Learning with Linear Function Approximation

2020-10-08 · Huozhi Zhou, Jinglin Chen, Lav R. Varshney, Ashish Jagmohan

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Minimax Weight Learning for Absorbing MDPs

2023-01-09 · Fengyin Li, Yuqiang Li, Xianyi Wu

Reinforcement learning policy evaluation problems are often modeled as finite or discounted/averaged infinite-horizon MDPs. In this paper, we study undiscounted off-policy policy evaluation for absorbing MDPs. Given the …

reinforcement-learningReinforcement Learning (RL)