List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper D4RL v2 (offline)

100.8Average ScoreEDAC
-3.223.850.877.8Nov 1, 2024
Updated 8mo ago

Evaluation results

MethodLinks
EDACCorrupted Element=action2024.11100.8
TRACERCorrupted Element=action2024.1192.8
RIQLCorrupted Element=action2024.1190.6
TRACERCorrupted Element=reward2024.1185.7
RIQLCorrupted Element=reward2024.1184.8
CQLCorrupted Element=action2024.1176.3
IQLCorrupted Element=observation2024.1170.8
CQLCorrupted Element=observation2024.1169.8
IQLCorrupted Element=action2024.1169.7
TRACERCorrupted Element=observation2024.1162.7
IQLCorrupted Element=dynamics2024.1162.4
UWMSGCorrupted Element=action2024.1160.8
MSGCorrupted Element=action2024.1153.4
RIQLCorrupted Element=observation2024.1152
CQLCorrupted Element=dynamics2024.1152
RIQLCorrupted Element=dynamics2024.1151.5
TRACERCorrupted Element=dynamics2024.1149.8
UWMSGCorrupted Element=observation2024.1142.8
BCCorrupted Element=reward2024.1137.6
MSGCorrupted Element=dynamics2024.1124.9
BCCorrupted Element=action2024.1122.8
BCCorrupted Element=observation2024.1121.5
BCCorrupted Element=dynamics2024.1119.5
IQLCorrupted Element=reward2024.1118.8
CQLCorrupted Element=reward2024.1115.4
UWMSGCorrupted Element=dynamics2024.1112.4
MSGCorrupted Element=observation2024.116.9
MSGCorrupted Element=reward2024.116.1
EDACCorrupted Element=reward2024.112.6
UWMSGCorrupted Element=reward2024.111.3
EDACCorrupted Element=observation2024.111
EDACCorrupted Element=dynamics2024.110.8