List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL MuJoCo Walker2d-e v2 (expert)

110.2Normalized ScoreTSRL
-4.30425.42355.1584.877Jun 7, 2023
Updated 8mo ago

Evaluation results

MethodLinks
TSRLRatio=1, Size=1M2023.06110.2
IQLRatio=1, Size=1M2023.06109.7
TD3+BCRatio=1, Size=1M2023.06108.2
BCRatio=1, Size=1M2023.06107.9
DOGERatio=1, Size=1M2023.06107.3
TSRLRatio=1/100, Size=10k2023.06102.2
CQLRatio=1, Size=1M2023.06101.3
DOGERatio=1/100, Size=10k2023.0672.1
CQLRatio=1/100, Size=10k2023.0641.6
TD3+BCRatio=1/100, Size=10k2023.0623.8
IQLRatio=1/100, Size=10k2023.0612.6
BCRatio=1/100, Size=10k2023.0610.4
MOPORatio=1/100, Size=10k2023.061.4
MOPORatio=1, Size=1M2023.060.1