Offline Inverse Reinforcement Learning on D4RL Hopper Medium-Replay v2
2,417.83Cumulative RewardValueDICE
Evaluation Results
| Method | Links | |
|---|---|---|
| ValueDICEExpert Demonstrations=1,0002023.02 | 2,417.83 | |
| Offline ML-IRLExpert Demonstrations=1,0002023.02 | 2,395.03 | |
| CLAREExpert Demonstrations=1,0002023.02 | 2,369.79 | |
| BCExpert Demonstrations=1,0002023.02 | 843.59 |