Locomotion on D4RL Gym (random-medium)
52.7HalfCheetah ScoreMOPO
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MOPOseeds=5, iteration=last training, score_type=normalized2024.03 | 52.7 | 19.9 | 40.2 | |
| A2POseeds=5, iteration=last training, score_type=normalized2024.03 | 48.5 | 62.1 | 82.3 | |
| Diffusion-QLseeds=5, iteration=last training, score_type=normalized2024.03 | 48.4 | 6.9 | 3.3 | |
| TD3+BCseeds=5, iteration=last training, score_type=normalized2024.03 | 47.7 | 7.4 | 10.7 | |
| CQL+AWseeds=5, iteration=last training, score_type=normalized2024.03 | 46.5 | 22.6 | 82 | |
| EQLseeds=5, iteration=last training, score_type=normalized2024.03 | 42.3 | 1.7 | 31.4 | |
| IQLseeds=5, iteration=last training, score_type=normalized2024.03 | 42.2 | 6.2 | 54.6 | |
| CQLseeds=5, iteration=last training, score_type=normalized2024.03 | 31.9 | 3.3 | 0.2 | |
| LAPOseeds=5, iteration=last training, score_type=normalized2024.03 | 18.5 | 4.2 | 23.6 | |
| BCQseeds=5, iteration=last training, score_type=normalized2024.03 | 12.7 | 9.2 | 0.2 | |
| AWACseeds=5, iteration=last training, score_type=normalized2024.03 | 6.5 | 19.5 | 0 | |
| BCseeds=5, iteration=last training, score_type=normalized2024.03 | 2.3 | 23.2 | 19.2 |