arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.07219cs.LGstat.ML
收藏

D4RL:深度数据驱动的强化学习数据集

D4RL: Datasets for Deep Data-Driven Reinforcement Learning

UC Berkeley(加州大学伯克利分校);Google Brain(谷歌大脑)

Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine

摘要:

离线强化学习(RL)设置(也称为全批RL),其中从静态数据集学习策略,这是令人信服的,因为进步使RL方法能够利用以前收集的大型数据集,就像大型数据集的兴起如何推动监督学习的结果一样。然而,现有的在线RL基准不是针对离线设置而定制的,并且现有的离线RL基准仅限于由部分训练的代理生成的数据,使得离线RL的进展难以测量。在这项工作中,我们介绍了专门为离线设置设计的基准,由与离线RL的真实应用相关的数据集的关键属性指导。以数据集收集为重点,此类属性的示例包括:通过手工设计的控制器和人类演示者生成的数据集,代理在同一环境中执行不同任务的多任务数据集,以及使用混合策略收集的数据集。通过超越简单的基准任务和部分训练的RL代理收集的数据,我们揭示了现有算法的重要和未被重视的缺陷。为了促进研究,我们发布了我们的基准任务和数据集,对现有算法进行了全面评估,评估协议和开源示例。这是社区识别现有离线RL方法中的缺点的共同起点,也是在这一新兴领域取得进展的协作路线。

英文摘要:

The offline reinforcement learning (RL) setting (also known as full batch RL), where a policy is learned from a static dataset, is compelling as progress enables RL methods to take advantage of large, previously-collected datasets, much like how the rise of large datasets has fueled results in supervised learning. However, existing online RL benchmarks are not tailored towards the offline setting and existing offline RL benchmarks are restricted to data generated by partially-trained agents, making progress in offline RL difficult to measure. In this work, we introduce benchmarks specifically designed for the offline setting, guided by key properties of datasets relevant to real-world applications of offline RL. With a focus on dataset collection, examples of such properties include: datasets generated via hand-designed controllers and human demonstrators, multitask datasets where an agent performs different tasks in the same environment, and datasets collected with mixtures of policies. By moving beyond simple benchmark tasks and data collected by partially-trained RL agents, we reveal important and unappreciated deficiencies of existing algorithms. To facilitate research, we have released our benchmark tasks and datasets with a comprehensive evaluation of existing algorithms, an evaluation protocol, and open-source examples. This serves as a common starting point for the community to identify shortcomings in existing offline RL methods and a collaborative route for progress in this emerging area.

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。

↑