中文
相关论文

相关论文: Know Your Boundaries: The Necessity of Explicit Be…

200 篇论文

Offline reinforcement learning (RL) algorithms can acquire effective policies by utilizing previously collected experience, without any online interaction. It is widely understood that offline RL is able to extract good policies even from…

机器学习 · 计算机科学 2022-04-13 Aviral Kumar , Joey Hong , Anikait Singh , Sergey Levine

Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data. Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms take the approach of constraining or regularizing…

机器学习 · 计算机科学 2021-12-06 Scott Fujimoto , Shixiang Shane Gu

Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly…

机器学习 · 计算机科学 2024-08-06 Shirong Liu , Chenjia Bai , Zixian Guo , Hao Zhang , Gaurav Sharma , Yang Liu

Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may…

机器学习 · 计算机科学 2022-10-26 Yi Zhao , Rinu Boney , Alexander Ilin , Juho Kannala , Joni Pajarinen

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

机器学习 · 计算机科学 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana

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) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…

机器学习 · 计算机科学 2021-09-24 Aviral Kumar , Anikait Singh , Stephen Tian , Chelsea Finn , Sergey Levine

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

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

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

The ability to discover optimal behaviour from fixed data sets has the potential to transfer the successes of reinforcement learning (RL) to domains where data collection is acutely problematic. In this offline setting, a key challenge is…

机器学习 · 计算机科学 2022-11-23 Alex Beeson , Giovanni Montana

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

机器人学 · 计算机科学 2025-09-29 Lars Ankile , Zhenyu Jiang , Rocky Duan , Guanya Shi , Pieter Abbeel , Anusha Nagabandi

Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This great promise has motivated a large amount of research that hopes to replicate…

Offline reinforcement learning (RL) defines a sample-efficient learning paradigm, where a policy is learned from static and previously collected datasets without additional interaction with the environment. The major obstacle to offline RL…

机器学习 · 计算机科学 2022-11-16 Yunfan Zhou , Xijun Li , Qingyu Qu

Offline reinforcement learning (RL) methods aim to learn optimal policies with access only to trajectories in a fixed dataset. Policy constraint methods formulate policy learning as an optimization problem that balances maximizing reward…

机器学习 · 计算机科学 2025-03-04 Padmanaba Srinivasan , William Knottenbelt

While imitation learning requires access to high-quality data, offline reinforcement learning (RL) should, in principle, perform similarly or better with substantially lower data quality by using a value function. However, current results…

机器学习 · 计算机科学 2024-10-30 Seohong Park , Kevin Frans , Sergey Levine , Aviral Kumar

Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap,…

机器学习 · 计算机科学 2021-02-09 Rongjun Qin , Songyi Gao , Xingyuan Zhang , Zhen Xu , Shengkai Huang , Zewen Li , Weinan Zhang , Yang Yu

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

机器学习 · 计算机科学 2025-12-24 Yuanhao Chen , Qi Liu , Pengbin Chen , Zhongjian Qiao , Yanjie Li

In offline reinforcement learning, weighted regression is a common method to ensure the learned policy stays close to the behavior policy and to prevent selecting out-of-sample actions. In this work, we show that due to the limited…

机器学习 · 计算机科学 2023-03-01 Huayu Chen , Cheng Lu , Chengyang Ying , Hang Su , Jun Zhu

Offline reinforcement learning (RL) tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. Despite the potential to surpass the behavioral policies, RL-based methods are generally…

机器学习 · 计算机科学 2022-01-13 Minghuan Liu , Hanye Zhao , Zhengyu Yang , Jian Shen , Weinan Zhang , Li Zhao , Tie-Yan Liu
‹ 上一页 1 2 3 10 下一页 ›