Offline Reinforcement Learning on D4RL Gym-MuJoCo v2 (test) (Medium, Medium-Replay, Medium-Expert)
74.1HalfCheetah-Medium ReturnQDQ
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| QDQDataset version=-v2, Number of seeds=52024.10 | 74.1 | 99 | 86.9 | 63.7 | 102.4 | 93.2 | 99.3 | 113.5 | 115.9 | 848 | |
| EDACDataset version=-v2, Number of seeds=52024.10 | 65.9 | 101.6 | 92.5 | 61.3 | 101 | 87.1 | 106.3 | 110.7 | 114.7 | 841.1 | |
| MCQDataset version=-v2, Number of seeds=52024.10 | 64.3 | 78.4 | 91 | 56.8 | 101.6 | 91.3 | 87.3 | 112.3 | 114.2 | 797.4 | |
| PBRLDataset version=-v2, Number of seeds=52024.10 | 57.9 | 75.3 | 89.6 | 45.1 | 100.6 | 77.7 | 92.3 | 110.8 | 110.1 | 759.4 | |
| TD3+BCDataset version=-v2, Number of seeds=52024.10 | 48.3 | 59.3 | 83.7 | 44.6 | 60.9 | 81.8 | 90.7 | 98 | 110.1 | 684.6 | |
| IQLDataset version=-v2, Number of seeds=52024.10 | 47.4 | 66.3 | 78.3 | 44.2 | 94.7 | 73.8 | 86.7 | 91.5 | 109.6 | 698.5 | |
| CQLDataset version=-v2, Number of seeds=52024.10 | 44 | 58.5 | 72.5 | 45.5 | 95 | 77.2 | 91.6 | 105.4 | 108.8 | 677.4 | |
| AWACDataset version=-v2, Number of seeds=52024.10 | 43.5 | 57 | 72.4 | 40.5 | 37.2 | 27 | 42.8 | 55.8 | 74.5 | 450.7 | |
| BCDataset version=-v2, Number of seeds=52024.10 | 42.6 | 52.9 | 75.3 | 36.6 | 18.1 | 26 | 55.2 | 52.5 | 107.5 | 466.7 | |
| DTDataset version=-v2, Number of seeds=52024.10 | 42.6 | 67.6 | 74 | 36.6 | 82.7 | 66.6 | 86.8 | 107.6 | 108.1 | 672.6 | |
| UWACDataset version=-v2, Number of seeds=52024.10 | 42.2 | 50.9 | 75.4 | 35.9 | 25.3 | 23.6 | 42.7 | 44.9 | 96.5 | 437.4 |