Offline Reinforcement Learning on D4RL Antmaze umaze, medium, large v0
92.3AntMaze UMaze v0 ScoreMISA
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| MISA2022.10 | 92.3 | 89.1 | 63 | 62.8 | 17.5 | 23.4 | 348.1 | |
| IQL2022.10 | 87.5 | 62.2 | 71.2 | 70 | 39.6 | 47.5 | 378 | |
| TD3+BC2022.10 | 78.6 | 71.4 | 10.6 | 3 | 0.2 | 0 | 163.8 | |
| CQL2022.10 | 74 | 84 | 61.2 | 53.7 | 15.8 | 14.9 | 303.6 | |
| OneStep RL2022.10 | 64.3 | 60.7 | 0.3 | 0 | 0 | 0 | 125.3 | |
| 10%BC2022.10 | 62.8 | 50.2 | 5.4 | 9.8 | 0 | 6 | 134.2 | |
| DT2022.10 | 59.2 | 53 | 0 | 0 | 0 | 0 | 112.2 | |
| AWAC2022.10 | 56.7 | 49.3 | 0 | 0.7 | 0 | 1 | 107.7 | |
| BC2022.10 | 54.6 | 45.6 | 0 | 0 | 0 | 0 | 100.2 |