Offline Reinforcement Learning on D4RL Expert v2
96.7HalfCheetah Normalized ScoreTD3+BC
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TD3+BCseeds=5, hyperparameter tuning=none, evaluation protocol=average over final 10 evaluations2021.06 | 96.7 | 107.8 | 110.2 |
Loading the SOTA2 catalog…