Locomotion on D4RL Gym (medium-replay)
53.1HalfCheetah ReturnMOPO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MOPOseeds=5, iteration=last training, score_type=normalized2024.03 | 53.1 | 67.5 | 39 | |
| Diffusion-QLseeds=5, iteration=last training, score_type=normalized2024.03 | 47.8 | 101.3 | 95.5 | |
| CQL+AWseeds=5, iteration=last training, score_type=normalized2024.03 | 47 | 99 | 87 | |
| CQLseeds=5, iteration=last training, score_type=normalized2024.03 | 45.5 | 95 | 81.6 | |
| A2POseeds=5, iteration=last training, score_type=normalized2024.03 | 44.8 | 101.6 | 82.8 | |
| TD3+BCseeds=5, iteration=last training, score_type=normalized2024.03 | 44.6 | 60.9 | 81.8 | |
| EQLseeds=5, iteration=last training, score_type=normalized2024.03 | 44.5 | 98.1 | 76.6 | |
| IQLseeds=5, iteration=last training, score_type=normalized2024.03 | 44.2 | 94.7 | 73.9 | |
| LAPOseeds=5, iteration=last training, score_type=normalized2024.03 | 41.9 | 50.1 | 60.6 | |
| AWACseeds=5, iteration=last training, score_type=normalized2024.03 | 40.5 | 37.2 | 27 | |
| BCQseeds=5, iteration=last training, score_type=normalized2024.03 | 40.4 | 53.3 | 52.1 | |
| BCseeds=5, iteration=last training, score_type=normalized2024.03 | 36.6 | 18.1 | 26 |