Offline Inverse Reinforcement Learning on MuJoCo walker2d (medium-replay)
5,383.98Avg RewardExpert Performance
Evaluation Results
| Method | Links | |
|---|---|---|
| Expert Performanceexpert demonstrations=50002023.02 | 5,383.98 | |
| Offline ML-IRLexpert demonstrations=50002023.02 | 3,995.32 | |
| ValueDICEexpert demonstrations=50002023.02 | 3,191.47 | |
| BCexpert demonstrations=50002023.02 | 2,328.75 | |
| CLAREexpert demonstrations=50002023.02 | 291.71 |