Offline Reinforcement Learning on D4RL AntMaze Medium-Diverse v0
10.6Normalized ScoreTD3+BC
Evaluation Results
| Method | Links | |
|---|---|---|
| TD3+BCEvaluations=final 10, Seeds=5, State feature normalization=false2021.06 | 10.6 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| TD3+BCEvaluations=final 10, Seeds=5, State feature normalization=false2021.06 | 10.6 |