arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.04413cs.LGcs.AI
收藏

超越均匀采样:基于不均衡数据集的离线强化学习

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Massachusetts Institute of Technology(麻省理工学院);MIT-IBM Lab(麻省理工学院-IBM实验室);Aalto University(阿尔托大学);University of Washington(华盛顿大学)

Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik, Abhishek Bhandwaldar, Akash Srivastava, Joni Pajarinen, Romain Laroche, Abhishek Gupta, Pulkit Agrawal

AI总结:

针对离线强化学习在不均衡数据集上因均匀采样导致策略模仿次优动作的问题,提出一种仅约束于优质数据的采样策略,作为即插即用模块显著提升性能。

摘要:

离线策略学习旨在利用现有的轨迹数据集学习决策策略,而无需收集额外数据。使用强化学习(RL)而非监督学习技术(如行为克隆)的主要动机是寻找一种策略,使其平均回报高于构成数据集的轨迹。然而,我们通过实验发现,当数据集由次优轨迹主导时,最先进的离线RL算法并不能显著提高数据集中轨迹的平均回报。我们认为这是由于当前离线RL算法假设策略需与数据集中的轨迹保持接近。如果数据集主要由次优轨迹组成,这一假设会迫使策略模仿次优动作。我们通过提出一种采样策略来解决这一问题,该策略使策略仅受限于“优质数据”,而非数据集中的所有动作(即均匀采样)。我们展示了该采样策略的一种实现,以及一个可作为标准离线RL算法即插即用模块的算法。我们的评估在72个不均衡数据集、D4RL数据集以及三种不同的离线RL算法上展示了显著的性能提升。代码可在 https://github.com/Improbable-AI/dw-offline-rl 获取。

英文摘要:

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 techniques such as behavior cloning is to find a policy that achieves a higher average return than the trajectories constituting the dataset. However, we empirically find that when a dataset is dominated by suboptimal trajectories, state-of-the-art offline RL algorithms do not substantially improve over the average return of trajectories in the dataset. We argue this is due to an assumption made by current offline RL algorithms of staying close to the trajectories in the dataset. If the dataset primarily consists of sub-optimal trajectories, this assumption forces the policy to mimic the suboptimal actions. We overcome this issue by proposing a sampling strategy that enables the policy to only be constrained to ``good data" rather than all actions in the dataset (i.e., uniform sampling). We present a realization of the sampling strategy and an algorithm that can be used as a plug-and-play module in standard offline RL algorithms. Our evaluation demonstrates significant performance gains in 72 imbalanced datasets, D4RL dataset, and across three different offline RL algorithms. Code is available at https://github.com/Improbable-AI/dw-offline-rl.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑