paper-with-me

홈 › Papers

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 \underline{C}lipping \underline{B}ound (\texttt{SCB}), and instantiate this framework in both the adversarial Multi-armed Bandit (MAB) setting and the adversarial MDP setting. Through this framework, we achieve the first minimax optimal expected regret bound and the first high-probability regret bound in scale-free adversarial MABs, resolving an open problem raised in \cite{hadiji2023adaptation}. On adversarial MDPs, our framework also give birth to the first scale-free RL algorithm with a $\tilde{\mathcal{O}}(\sqrt{T})$ high-probability regret guarantee.

📄 PDF Abstract BibTeX arXiv:2403.00930

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

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)

Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

2019-11-10 · NeurIPS 2019 12 · Xueying Bai, Jian Guan, Hongning Wang

Reinforcement learning is well suited for optimizing policies of recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with the real environment, and thus are e…

Generative Adversarial NetworkModel-based Reinforcement LearningRecommendation Systemsreinforcement-learning+2

Model-Free $μ$ Synthesis via Adversarial Reinforcement Learning

2021-11-30 · Darioush Keivan, Aaron Havens, Peter Seiler, Geir Dullerud 외

Motivated by the recent empirical success of policy-based reinforcement learning (RL), there has been a research trend studying the performance of policy-based RL methods on standard control benchmark problems. In this p…

modelreinforcement-learningReinforcement LearningReinforcement Learning (RL)

A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation

2019-12-01 · NeurIPS 2019 12 · Xueying Bai, Jian Guan, Hongning Wang

Reinforcement learning is effective in optimizing policies for recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with a real environment, and thus are expen…

Generative Adversarial NetworkModel-based Reinforcement LearningRecommendation Systemsreinforcement-learning+2

Toward Evaluating Robustness of Deep Reinforcement Learning with Continuous Control

2020-05-01 · ICLR 2020 1 · Tsui-Wei Weng, Krishnamurthy (Dj) Dvijotham*, Jonathan Uesato*, Kai Xiao* 외

Deep reinforcement learning has achieved great success in many previously difficult reinforcement learning tasks, yet recent studies show that deep RL agents are also unavoidably susceptible to adversarial perturbations,…

continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCo+3