Locomotion on D4RL Gym (medium)
51.1HalfCheetah ScoreDiffusion-QL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Diffusion-QLseeds=5, iteration=last training, score_type=normalized2024.03 | 51.1 | 90.5 | 87 | |
| CQL+AWseeds=5, iteration=last training, score_type=normalized2024.03 | 49 | 71 | 83 | |
| TD3+BCseeds=5, iteration=last training, score_type=normalized2024.03 | 48.3 | 59.3 | 83.7 | |
| IQLseeds=5, iteration=last training, score_type=normalized2024.03 | 47.4 | 66.3 | 78.3 | |
| EQLseeds=5, iteration=last training, score_type=normalized2024.03 | 47.2 | 74.6 | 83.2 | |
| A2POseeds=5, iteration=last training, score_type=normalized2024.03 | 47.1 | 80.3 | 84.9 | |
| BCQseeds=5, iteration=last training, score_type=normalized2024.03 | 47 | 56.7 | 72.6 | |
| LAPOseeds=5, iteration=last training, score_type=normalized2024.03 | 46 | 51.6 | 80.8 | |
| CQLseeds=5, iteration=last training, score_type=normalized2024.03 | 44 | 58.5 | 72.5 | |
| AWACseeds=5, iteration=last training, score_type=normalized2024.03 | 43.5 | 57 | 72.4 | |
| BCseeds=5, iteration=last training, score_type=normalized2024.03 | 42.6 | 52.9 | 75.3 | |
| MOPOseeds=5, iteration=last training, score_type=normalized2024.03 | 42.3 | 28 | 17.8 |