Offline Inverse Reinforcement Learning on D4RL Hopper Medium-Expert v2
3,366.23Cumulative RewardOffline ML-IRL
Evaluation Results
| Method | Links | |
|---|---|---|
| Offline ML-IRLExpert Demonstrations=1,0002023.02 | 3,366.23 | |
| CLAREExpert Demonstrations=1,0002023.02 | 3,071.31 | |
| ValueDICEExpert Demonstrations=1,0002023.02 | 2,417.83 | |
| BCExpert Demonstrations=1,0002023.02 | 843.59 |