Offline Inverse Reinforcement Learning on D4RL Walker2d Medium-Expert v2
4,049.43Cumulative RewardOffline ML-IRL
Evaluation Results
| Method | Links | |
|---|---|---|
| Offline ML-IRLExpert Demonstrations=1,0002023.02 | 4,049.43 | |
| ValueDICEExpert Demonstrations=1,0002023.02 | 1,794.97 | |
| BCExpert Demonstrations=1,0002023.02 | 1,248.13 | |
| CLAREExpert Demonstrations=1,0002023.02 | 548.59 |