Offline Hierarchical Reinforcement Learning: Enable Large-Scale Training in HRL | |
Yuqiao Wu2; Haifeng Zhang2; Jun Wang1 | |
2023 | |
会议日期 | 2023-11-27 |
会议地点 | Nanjing |
英文摘要 | Large-scale trained models have shown significant success across various machine learning domains, leading researchers to explore their application in decision-making tasks. Hierarchical decomposition, particularly hierarchical reinforcement learning, is a vital approach to solving complex tasks by breaking them down into simpler sub-tasks. However, large-scale training a model under such a hierarchy remains challenging. Existing hierarchical reinforcement learning methods are formulated in online settings, which limits their scalability for large-scale training with sequence modeling. To address this limitation, we introduce a hierarchical structure into transformer-based offline RL. Our proposed approach, OF &D, is a contrastive learning framework that learns state-action temporal abstractions and hierarchical policies. We achieve state-of-the-art performance on the D4RL benchmark. Furthermore, this work paves the way for large-scale training in hierarchical reinforcement learning, facilitating the development of general long-horizon decision models. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/58534] |
专题 | 复杂系统认知与决策实验室_群体决策智能团队 |
作者单位 | 1.UCL 2.CASIA |
推荐引用方式 GB/T 7714 | Yuqiao Wu,Haifeng Zhang,Jun Wang. Offline Hierarchical Reinforcement Learning: Enable Large-Scale Training in HRL[C]. 见:. Nanjing. 2023-11-27. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论