XuGW-Kevin/DrM
DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements in sample efficiency and asymptotic performance across diverse domains.
PythonMIT
Stargazers
- Aaronminer1
- ACE-RL
- ACG-YAO
- Artimisu
- c7wTsinghua University
- CRLqinliang
- DrM-RL
- Dyl777
- emlynw
- FrankZheng2022University of Maryland College Park
- gemcollectorTsinghua University
- GNAQHarbin Institute of Technology
- godnpeter
- GuanxingLuSoutheast -> Tsinghua
- Guozheng-MaNanyang Technological University
- initial-h
- JeffCarpenterCanada
- JingzheShiTsinghua University
- jonzamoraUniversity of Southern California
- joonleeskyKAIST
- JusperLee@thu-ml
- kinalmehtaQualcomm
- NagisaZj
- PremierTACO
- puyuan1996China
- shuiqicheng
- srzerTsinghua University
- TakuyaHiraokaTokyo-3, Japan
- timokleinUniversity of Vienna
- TMatsThe University of Tokyo @matsuolab @matsuolab-research
- XuGW-KevinTsinghua University
- xuhuazhe
- yang-zj1026University of Southern California
- YanjieZeShanghai Jiao Tong University
- zerlinwangTsinghua University
- zzmtsvv