Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Offline multitask Reinforcement Learning on D4RL Antmaze medium-diverse

631Episodic Return

DiSPO

220.2326.85433.5540.15Mar 10, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.03
631
2024.03
418
2024.03
403
2024.03
394
2024.03
294
2024.03
266
2024.03
236