Locomotion on D4RL Gym Aggregate
1,563.3Gym TotalA2PO
Evaluation Results
| Method | Links | |
|---|---|---|
| A2POaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 1,563.3 | |
| CQL+AWaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 1,376.9 | |
| Diffusion-QLaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 1,302.1 | |
| IQLaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 1,183.9 | |
| EQLaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 1,107.2 | |
| LAPOaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 1,026.8 | |
| TD3+BCaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 1,010.6 | |
| CQLaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 784.4 | |
| AWACaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 710.9 | |
| BCQaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 657.6 | |
| MOPOaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 628.8 | |
| BCaggregation=Sum of normalized scores, seeds=5, iteration=last training2024.03 | 604.2 |