paper-with-me

홈 › Papers

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

2023-05-24 · NeurIPS 2023 11 · Xiang Ji, Gen Li

A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting. The existing algorithms either fail to achieve regret optimality or have to incur a high memory and computational cost. In addition, existing optimal algorithms all require a long burn-in time in order to achieve optimal sample efficiency, i.e., their optimality is not guaranteed unless sample size surpasses a high threshold. We address both open problems by introducing a model-free algorithm that employs variance reduction and a novel technique that switches the execution policy in a slow-yet-adaptive manner. This is the first regret-optimal model-free algorithm in the discounted setting, with the additional benefit of a low burn-in time.

📄 PDF Abstract BibTeX arXiv:2305.15546

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs

2020-10-01 · NeurIPS 2021 12 · Jiafan He, Dongruo Zhou, Quanquan Gu

We study the reinforcement learning problem for discounted Markov Decision Processes (MDPs) under the tabular setting. We propose a model-based algorithm named UCBVI-$\gamma$, which is based on the \emph{optimism in the …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes

2019-10-15 · ICML 2020 1 · Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Hiteshi Sharma 외

Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-…

Multi-Armed Banditsreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping

2020-06-23 · Dongruo Zhou, Jiafan He, Quanquan Gu

Modern tasks in reinforcement learning have large state and action spaces. To deal with them efficiently, one often uses predefined feature mapping to represent states and actions in a low-dimensional space. In this pape…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs

2022-05-18 · Ian A. Kash, Lev Reyzin, Zishun Yu

Reinforcement learning generalizes multi-armed bandit problems with additional difficulties of a longer planning horizon and unknown transition kernel. We explore a black-box reduction from discounted infinite-horizon ta…

Multi-Armed Banditsreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Variational Regret Bounds for Reinforcement Learning

2019-05-14 · Pratik Gajane, Ronald Ortner, Peter Auer

We consider undiscounted reinforcement learning in Markov decision processes (MDPs) where both the reward functions and the state-transition probabilities may vary (gradually or abruptly) over time. For this problem sett…

General Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)