Locomotion on D4RL Gym (medium-expert)
96.8HalfCheetah ScoreDiffusion-QL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Diffusion-QLseeds=5, iteration=last training, score_type=normalized2024.03 | 96.8 | 111.1 | 110.1 | |
| A2POseeds=5, iteration=last training, score_type=normalized2024.03 | 95.6 | 113.4 | 112.1 | |
| LAPOseeds=5, iteration=last training, score_type=normalized2024.03 | 94.2 | 111 | 110.9 | |
| CQLseeds=5, iteration=last training, score_type=normalized2024.03 | 91.6 | 105.4 | 108.8 | |
| TD3+BCseeds=5, iteration=last training, score_type=normalized2024.03 | 90.7 | 98 | 110.1 | |
| EQLseeds=5, iteration=last training, score_type=normalized2024.03 | 90.6 | 105.5 | 110.2 | |
| BCQseeds=5, iteration=last training, score_type=normalized2024.03 | 89.1 | 81.8 | 109 | |
| IQLseeds=5, iteration=last training, score_type=normalized2024.03 | 86.7 | 91.5 | 109.6 | |
| CQL+AWseeds=5, iteration=last training, score_type=normalized2024.03 | 84 | 91 | 109 | |
| MOPOseeds=5, iteration=last training, score_type=normalized2024.03 | 63.3 | 23.7 | 44.6 | |
| BCseeds=5, iteration=last training, score_type=normalized2024.03 | 55.2 | 52.5 | 107.5 | |
| AWACseeds=5, iteration=last training, score_type=normalized2024.03 | 42.8 | 55.8 | 74.5 |