Locomotion on D4RL Gym (random-medium-expert)
90.6HalfCheetah ReturnA2PO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| A2POseeds=5, iteration=last training, score_type=normalized2024.03 | 90.6 | 107.8 | 97.7 | |
| Diffusion-QLseeds=5, iteration=last training, score_type=normalized2024.03 | 81.2 | 70.1 | 56.6 | |
| CQL+AWseeds=5, iteration=last training, score_type=normalized2024.03 | 76.8 | 71.8 | 58.3 | |
| LAPOseeds=5, iteration=last training, score_type=normalized2024.03 | 71.1 | 66.6 | 60.4 | |
| TD3+BCseeds=5, iteration=last training, score_type=normalized2024.03 | 62.3 | 60.5 | 15.7 | |
| IQLseeds=5, iteration=last training, score_type=normalized2024.03 | 61.6 | 57.9 | 90.8 | |
| EQLseeds=5, iteration=last training, score_type=normalized2024.03 | 42.8 | 72.4 | 61 | |
| MOPOseeds=5, iteration=last training, score_type=normalized2024.03 | 26.7 | 13.3 | 56.4 | |
| BCQseeds=5, iteration=last training, score_type=normalized2024.03 | 15.9 | 4 | 2.4 | |
| CQLseeds=5, iteration=last training, score_type=normalized2024.03 | 13.5 | 9.4 | 0.1 | |
| BCseeds=5, iteration=last training, score_type=normalized2024.03 | 2.3 | 27.4 | 24.6 | |
| AWACseeds=5, iteration=last training, score_type=normalized2024.03 | 2.3 | 8.6 | -0.4 |