List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Halfcheetah D4RL v2 (offline)

56Average ScoreUWMSG
-2.44812.72627.943.074Nov 1, 2024
Updated 8mo ago

Evaluation results

MethodLinks
UWMSGCorrupted Element=action2024.1156
MSGCorrupted Element=action2024.1152
EDACCorrupted Element=action2024.1147.4
TRACERCorrupted Element=dynamics2024.1143.8
RIQLCorrupted Element=reward2024.1143.6
RIQLCorrupted Element=dynamics2024.1143.1
RIQLCorrupted Element=action2024.1142.9
TRACERCorrupted Element=action2024.1142.9
IQLCorrupted Element=reward2024.1142.3
IQLCorrupted Element=action2024.1142.2
TRACERCorrupted Element=reward2024.1140
EDACCorrupted Element=reward2024.1138.6
IQLCorrupted Element=dynamics2024.1136.7
BCCorrupted Element=action2024.1135.8
BCCorrupted Element=reward2024.1135.8
BCCorrupted Element=dynamics2024.1135.8
UWMSGCorrupted Element=reward2024.1135.6
TRACERCorrupted Element=observation2024.1134.2
BCCorrupted Element=observation2024.1133.4
CQLCorrupted Element=reward2024.1132.6
CQLCorrupted Element=dynamics2024.1129.2
RIQLCorrupted Element=observation2024.1127.3
IQLCorrupted Element=observation2024.1121.4
CQLCorrupted Element=action2024.1119.9
MSGCorrupted Element=reward2024.1117.5
CQLCorrupted Element=observation2024.119
UWMSGCorrupted Element=observation2024.112.9
UWMSGCorrupted Element=dynamics2024.112.9
EDACCorrupted Element=observation2024.112.1
MSGCorrupted Element=dynamics2024.111.7
EDACCorrupted Element=dynamics2024.111.5
MSGCorrupted Element=observation2024.11-0.2