Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Offline multitask Reinforcement Learning on D4RL Antmaze large-play

306Average Episodic Return

DiSPO

120.88168.94217265.06Mar 10, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.03
306
2024.03
250
2024.03
248
2024.03
229
2024.03
165
2024.03
134
2024.03
128