中文
相关论文

相关论文: Improving Offline-to-Online Reinforcement Learning…

200 篇论文

Recent advance in deep offline reinforcement learning (RL) has made it possible to train strong robotic agents from offline datasets. However, depending on the quality of the trained agents and the application being considered, it is often…

机器人学 · 计算机科学 2021-11-02 Seunghyun Lee , Younggyo Seo , Kimin Lee , Pieter Abbeel , Jinwoo Shin

Reinforcement learning (RL) with limited samples is common in real-world applications. However, offline RL performance under this constraint is often suboptimal. We consider an alternative approach to dealing with limited samples by…

机器学习 · 计算机科学 2025-11-14 Outongyi Lv , Yewei Yuan , Nana Liu

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

机器学习 · 计算机科学 2021-10-13 Ilya Kostrikov , Ashvin Nair , Sergey Levine

This paper presents advanced techniques of training diffusion policies for offline reinforcement learning (RL). At the core is a mean-reverting stochastic differential equation (SDE) that transfers a complex action distribution into a…

机器学习 · 计算机科学 2025-01-09 Ruoqi Zhang , Ziwei Luo , Jens Sjölund , Thomas B. Schön , Per Mattsson

Traditional offline reinforcement learning (RL) methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of…

机器学习 · 统计学 2025-07-16 Charles A. Hepburn , Yue Jin , Giovanni Montana

We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are…

机器学习 · 统计学 2022-07-28 Chengchun Shi , Shikai Luo , Yuan Le , Hongtu Zhu , Rui Song

Offline reinforcement learning (RL) has increasingly become the focus of the artificial intelligent research due to its wide real-world applications where the collection of data may be difficult, time-consuming, or costly. In this paper, we…

机器学习 · 计算机科学 2021-05-13 Chenyang Xi , Bo Tang , Jiajun Shen , Xinfu Liu , Feiyu Xiong , Xueying Li

Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience. However, learning solely from a static dataset can limit the performance due to the lack of exploration. To overcome it,…

机器学习 · 计算机科学 2024-07-23 Kai Zhao , Jianye Hao , Yi Ma , Jinyi Liu , Yan Zheng , Zhaopeng Meng

Offline reinforcement learning (RL) allows for the training of competent agents from offline datasets without any interaction with the environment. Online finetuning of such offline models can further improve performance. But how should we…

机器学习 · 计算机科学 2023-03-31 Yicheng Luo , Jackie Kay , Edward Grefenstette , Marc Peter Deisenroth

Offline reinforcement learning (RL) aims to learn a policy from a static dataset without further interactions with the environment. Collecting sufficiently large datasets for offline RL is exhausting since this data collection requires…

人工智能 · 计算机科学 2025-10-22 Jongchan Park , Mingyu Park , Donghwan Lee

Offline reinforcement learning (offline RL), which aims to find an optimal policy from a previously collected static dataset, bears algorithmic difficulties due to function approximation errors from out-of-distribution (OOD) data points. To…

机器学习 · 计算机科学 2021-10-06 Gaon An , Seungyong Moon , Jang-Hyun Kim , Hyun Oh Song

The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be…

信息论 · 计算机科学 2023-11-21 Kun Yang , Cong Shen , Jing Yang , Shu-ping Yeh , Jerry Sydir

Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in two settings: learning interactively in the environment (online RL), or learning from an offline dataset (offline RL). However, existing algorithms…

机器学习 · 计算机科学 2022-02-14 Tengyang Xie , Nan Jiang , Huan Wang , Caiming Xiong , Yu Bai

Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key challenge, however, is learning an accurate critic in large state--action spaces with limited…

人工智能 · 计算机科学 2026-05-21 Andrew Choi , Wei Xu

Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Built on offline RL algorithms, most O2O methods focus on the balance between RL objective and…

机器学习 · 计算机科学 2023-12-14 Yinmin Zhang , Jie Liu , Chuming Li , Yazhe Niu , Yaodong Yang , Yu Liu , Wanli Ouyang

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected,…

机器学习 · 计算机科学 2020-08-20 Aviral Kumar , Aurick Zhou , George Tucker , Sergey Levine

We consider the offline constrained reinforcement learning (RL) problem, in which the agent aims to compute a policy that maximizes expected return while satisfying given cost constraints, learning only from a pre-collected dataset. This…

机器学习 · 计算机科学 2022-04-20 Jongmin Lee , Cosmin Paduraru , Daniel J. Mankowitz , Nicolas Heess , Doina Precup , Kee-Eung Kim , Arthur Guez

The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. While policy constraints, conservatism, and other…

人工智能 · 计算机科学 2023-10-19 Jianlan Luo , Perry Dong , Jeffrey Wu , Aviral Kumar , Xinyang Geng , Sergey Levine

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…

机器学习 · 计算机科学 2021-02-12 Mengjiao Yang , Ofir Nachum

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed…

机器学习 · 计算机科学 2021-06-23 Hua Wei , Deheng Ye , Zhao Liu , Hao Wu , Bo Yuan , Qiang Fu , Wei Yang , Zhenhui Li
‹ 上一页 1 2 3 10 下一页 ›