Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets

Yihuan Mao, Chengjie Wu, Xi Chen, Hao Hu, Ji Jiang, Tianze Zhou, Tangjie Lv, Changjie Fan, Zhipeng Hu, Yi Wu, Yujing Hu, Chongjie Zhang

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Reinforcement Learning, Diversity in RL, Offline RL

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Previous literature on policy diversity in reinforcement learning (RL) either focuses on the online setting or ignores the policy performance. In contrast, offline RL, which aims to learn high-quality policies from batched data, has yet to fully leverage the intrinsic diversity of the offline dataset. Addressing this dichotomy and aiming to balance quality and diversity poses a significant challenge to extant methodologies. This paper introduces a novel approach, termed Stylized Offline RL (SORL), which is designed to extract high-performing, stylistically diverse policies from a dataset characterized by distinct behavioral patterns. Drawing inspiration from the venerable Expectation-Maximization (EM) algorithm, SORL innovatively alternates between policy learning and trajectory clustering, a mechanism that promotes policy diversification. To further augment policy performance, we introduce advantage-weighted style learning into the SORL framework. Experimental evaluations across multiple environments demonstrate the significant superiority of SORL over previous methods in extracting high-quality policies with diverse behaviors. A case in point is that SORL successfully learns strong policies with markedly distinct playing patterns from a real-world human dataset of a popular basketball video game "Dunk City Dynasty."

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: reinforcement learning

Submission Number: 1156