中文
相关论文

相关论文: The Role of Coverage in Online Reinforcement Learn…

200 篇论文

In online reinforcement learning (RL), instead of employing standard structural assumptions on Markov decision processes (MDPs), using a certain coverage condition (original from offline RL) is enough to ensure sample-efficient guarantees…

机器学习 · 统计学 2023-06-01 Fanghui Liu , Luca Viano , Volkan Cevher

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

机器学习 · 计算机科学 2023-05-25 Chenjie Mao

We consider the offline reinforcement learning problem, where the aim is to learn a decision making policy from logged data. Offline RL -- particularly when coupled with (value) function approximation to allow for generalization in large or…

机器学习 · 计算机科学 2022-08-31 Dylan J. Foster , Akshay Krishnamurthy , David Simchi-Levi , Yunzong Xu

Sample-efficiency guarantees for offline reinforcement learning (RL) often rely on strong assumptions on both the function classes (e.g., Bellman-completeness) and the data coverage (e.g., all-policy concentrability). Despite the recent…

机器学习 · 计算机科学 2022-06-29 Wenhao Zhan , Baihe Huang , Audrey Huang , Nan Jiang , Jason D. Lee

Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation…

机器学习 · 计算机科学 2020-10-23 Ruosong Wang , Dean P. Foster , Sham M. Kakade

We study offline reinforcement learning under $Q^\star$-approximation and partial coverage, a setting that motivates practical algorithms such as Conservative $Q$-Learning (CQL; Kumar et al., 2020) but has received limited theoretical…

机器学习 · 计算机科学 2026-02-13 Haolin Liu , Braham Snyder , Chen-Yu Wei

We revisit the problem of offline reinforcement learning with value function realizability but without Bellman completeness. Previous work by Xie and Jiang (2021) and Foster et al. (2022) left open the question whether a bounded…

机器学习 · 计算机科学 2024-03-27 Zeyu Jia , Alexander Rakhlin , Ayush Sekhari , Chen-Yu Wei

We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and non-uniform coverage, and has been relatively underexamined from a theoretical perspective.…

机器学习 · 计算机科学 2026-04-23 Matthew Zurek , Guy Zamir , Yudong Chen

We consider a challenging theoretical problem in offline reinforcement learning (RL): obtaining sample-efficiency guarantees with a dataset lacking sufficient coverage, under only realizability-type assumptions for the function…

机器学习 · 计算机科学 2022-06-16 Jinglin Chen , Nan Jiang

We hypothesize that empirically studying the sample complexity of offline reinforcement learning (RL) is crucial for the practical applications of RL in the real world. Several recent works have demonstrated the ability to learn policies…

机器学习 · 计算机科学 2022-01-03 Samin Yeasar Arnob , Riashat Islam , Doina Precup

Offline reinforcement learning (RL) aims to optimize the return given a fixed dataset of agent trajectories without additional interactions with the environment. While algorithm development has progressed rapidly, significant theoretical…

机器学习 · 计算机科学 2025-08-12 Fengdi Che

Exploration is a major challenge in reinforcement learning, especially for high-dimensional domains that require function approximation. We propose exploration objectives -- policy optimization objectives that enable downstream maximization…

机器学习 · 计算机科学 2024-06-06 Philip Amortila , Dylan J. Foster , Akshay Krishnamurthy

This article introduces the theory of offline reinforcement learning in large state spaces, where good policies are learned from historical data without online interactions with the environment. Key concepts introduced include expressivity…

机器学习 · 计算机科学 2025-10-07 Nan Jiang , Tengyang Xie

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated.…

机器学习 · 计算机科学 2021-03-09 Ruosong Wang , Yifan Wu , Ruslan Salakhutdinov , Sham M. Kakade

In offline reinforcement learning (RL), the absence of active exploration calls for attention on the model robustness to tackle the sim-to-real gap, where the discrepancy between the simulated and deployed environments can significantly…

机器学习 · 计算机科学 2024-06-28 He Wang , Laixi Shi , Yuejie Chi

This paper concerns the central issues of model robustness and sample efficiency in offline reinforcement learning (RL), which aims to learn to perform decision making from history data without active exploration. Due to uncertainties and…

机器学习 · 计算机科学 2024-01-01 Laixi Shi , Yuejie Chi

We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in…

机器学习 · 计算机科学 2024-02-21 Avinandan Bose , Simon Shaolei Du , Maryam Fazel

In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL)…

机器学习 · 计算机科学 2026-03-05 Debamita Ghosh , George K. Atia , Yue Wang

This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However,…

机器学习 · 统计学 2024-03-11 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi , Yuting Wei

Offline reinforcement learning (RL) leverages previously collected data for policy optimization without any further active exploration. Despite the recent interest in this problem, its theoretical results in neural network function…

机器学习 · 统计学 2022-12-15 Thanh Nguyen-Tang , Sunil Gupta , Hung Tran-The , Svetha Venkatesh
‹ 上一页 1 2 3 10 下一页 ›