paper-with-me

Papers

Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL

2021-06-22 · Weitong Zhang, Jiafan He, Dongruo Zhou, Amy Zhang, Quanquan Gu

The success of deep reinforcement learning (DRL) lies in its ability to learn a representation that is well-suited for the exploration and exploitation task. To understand how the choice of representation can improve the efficiency of reinforcement learning (RL), we study representation selection for a class of low-rank Markov Decision Processes (MDPs) where the transition kernel can be represented in a bilinear form. We propose an efficient algorithm, called ReLEX, for representation learning in both online and offline RL. Specifically, we show that the online version of ReLEX, called ReLEX-UCB, always performs no worse than the state-of-the-art algorithm without representation selection, and achieves a strictly better constant regret if the representation function class has a "coverage" property over the entire state-action space. For the offline counterpart, ReLEX-LCB, we show that the algorithm can find the optimal policy if the representation class can cover the state-action space and achieves gap-dependent sample complexity. This is the first result with constant sample complexity for representation learning in offline RL.

📄 PDF Abstract BibTeX arXiv:2106.11935

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningOffline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation Learning

Similar Papers 제목 키워드 기반

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

2022-07-29 · Shuang Qiu, Lingxiao Wang, Chenjia Bai, Zhuoran Yang 외

In view of its power in extracting feature representation, contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL), leading to efficient policy learni…

Contrastive LearningDeep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)+2

Provably Efficient CVaR RL in Low-rank MDPs

2023-11-20 · Yulai Zhao, Wenhao Zhan, Xiaoyan Hu, Ho-fung Leung 외

We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the Conditional Value at Risk (CVaR) with a fixed risk tolerance $\tau$. Prior theoretical work studying risk-sensitive RL focuses on the tabu…

Reinforcement Learning (RL)Representation Learning

A Kernel Perspective on Behavioural Metrics for Markov Decision Processes

2023-10-05 · Pablo Samuel Castro, Tyler Kastner, Prakash Panangaden, Mark Rowland

Behavioural metrics have been shown to be an effective mechanism for constructing representations in reinforcement learning. We present a novel perspective on behavioural metrics for Markov decision processes via the use…

reinforcement-learningReinforcement Learning

Efficient Duple Perturbation Robustness in Low-rank MDPs

2024-04-11 · Yang Hu, Haitong Ma, Bo Dai, Na Li

The pursuit of robustness has recently been a popular topic in reinforcement learning (RL) research, yet the existing methods generally suffer from efficiency issues that obstruct their real-world implementation. In this…

Reinforcement Learning (RL)

Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP

2023-06-21 · Jiacheng Guo, Zihao Li, Huazheng Wang, Mengdi Wang 외

In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact r…

DecoderEfficient ExplorationRepresentation Learning