Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Yilun Kong; Guozheng Ma; Qi Zhao; Haoyu Wang; Li Shen; Xueqian Wang; Dacheng Tao

2025 ICML ICML 2025

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Yilun Kong, Guozheng Ma, Qi Zhao, Haoyu Wang, Li Shen, Xueqian Wang, Dacheng Tao

Topics

Reinforcement Learning > Methods > Deep RL Reinforcement Learning > Methods > Offline RL

Keywords

decision transformer mixture-of-experts experts three-stage training parameter scalability task scalability

Download PDF