中文
相关论文

相关论文: Robust Policy Expansion for Offline-to-Online RL u…

200 篇论文

Offline-to-online reinforcement learning (RL) leverages both pre-trained offline policies and online policies trained for downstream tasks, aiming to improve data efficiency and accelerate performance enhancement. An existing approach,…

机器学习 · 计算机科学 2024-11-01 JaeYoon Kim , Junyu Xuan , Christy Liang , Farookh Hussain

Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in…

机器学习 · 计算机科学 2024-03-12 Rui Yang , Han Zhong , Jiawei Xu , Amy Zhang , Chongjie Zhang , Lei Han , Tong Zhang

To obtain a near-optimal policy with fewer interactions in Reinforcement Learning (RL), a promising approach involves the combination of offline RL, which enhances sample efficiency by leveraging offline datasets, and online RL, which…

机器学习 · 计算机科学 2024-11-18 Xiaoyu Wen , Xudong Yu , Rui Yang , Haoyuan Chen , Chenjia Bai , Zhen Wang

A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL. However, existing works heavily rely on the purity of the data,…

机器学习 · 计算机科学 2022-10-20 Chengqian Gao , Ke Xu , Liu Liu , Deheng Ye , Peilin Zhao , Zhiqiang Xu

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world…

机器学习 · 计算机科学 2024-08-13 Thanh Nguyen , Tung M. Luu , Tri Ton , Chang D. Yoo

It is desirable for policies to optimistically explore new states and behaviors during online reinforcement learning (RL) or fine-tuning, especially when prior offline data does not provide enough state coverage. However, exploration…

机器学习 · 计算机科学 2023-10-13 Max Sobol Mark , Archit Sharma , Fahim Tajwar , Rafael Rafailov , Sergey Levine , Chelsea Finn

Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human…

机器学习 · 计算机科学 2023-06-01 Philip J. Ball , Laura Smith , Ilya Kostrikov , Sergey Levine

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be…

机器学习 · 计算机科学 2022-10-25 Rui Yang , Chenjia Bai , Xiaoteng Ma , Zhaoran Wang , Chongjie Zhang , Lei Han

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…

机器学习 · 计算机科学 2023-10-18 Xiaohan Hu , Yi Ma , Chenjun Xiao , Yan Zheng , Jianye Hao

Offline reinforcement learning (RL) is a challenging setting where existing off-policy actor-critic methods perform poorly due to the overestimation of out-of-distribution state-action pairs. Thus, various additional augmentations are…

机器学习 · 计算机科学 2023-02-23 Zifeng Zhuang , Kun Lei , Jinxin Liu , Donglin Wang , Yilang Guo

Offline-to-online (O2O) reinforcement learning (RL) provides an effective means of leveraging an offline pre-trained policy as initialization to improve performance rapidly with limited online interactions. Recent studies often design…

机器学习 · 计算机科学 2024-12-30 Qin-Wen Luo , Ming-Kun Xie , Ye-Wen Wang , Sheng-Jun Huang

Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour. The second step has been widely studied in the…

In offline-to-online reinforcement learning (O2O-RL), policies are first safely trained offline using previously collected datasets and then further fine-tuned for tasks via limited online interactions. In a typical O2O-RL pipeline,…

机器学习 · 计算机科学 2026-05-07 Alper Kamil Bozkurt , Xiaoan Xu , Shangtong Zhang , Miroslav Pajic , Yuichi Motai

Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance. However, existing methods, effective as they are, suffer from…

机器学习 · 计算机科学 2023-05-26 Jianxiong Li , Xiao Hu , Haoran Xu , Jingjing Liu , Xianyuan Zhan , Ya-Qin Zhang

Offline reinforcement learning (offline RL) algorithms often require additional constraints or penalty terms to address distribution shift issues, such as adding implicit or explicit policy constraints during policy optimization to reduce…

机器学习 · 计算机科学 2025-06-19 Ranting Hu

We study data corruption robustness for reinforcement learning with human feedback (RLHF) in an offline setting. Given an offline dataset of pairs of trajectories along with feedback about human preferences, an $\varepsilon$-fraction of the…

机器学习 · 计算机科学 2024-02-13 Debmalya Mandal , Andi Nika , Parameswaran Kamalaruban , Adish Singla , Goran Radanović

The high costs and risks involved in extensive environment interactions hinder the practical application of current online safe reinforcement learning (RL) methods. While offline safe RL addresses this by learning policies from static…

机器学习 · 计算机科学 2026-01-26 Keru Chen , Honghao Wei , Zhigang Deng , Sen Lin

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly…

机器学习 · 计算机科学 2022-10-18 Yang Yue , Bingyi Kang , Xiao Ma , Zhongwen Xu , Gao Huang , Shuicheng Yan

We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the offline dataset, and the corruption level $\zeta\geq0$…

机器学习 · 计算机科学 2024-02-20 Chenlu Ye , Rui Yang , Quanquan Gu , Tong Zhang

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
‹ 上一页 1 2 3 10 下一页 ›