Inverse Reinforcement Learning on D4RL Hopper medium-expert
3,512ReturnExpert
Evaluation results
| Method | Links | |
|---|---|---|
| Expertreward setting=deterministic2025.10 | 3,512 | |
| DistIRLreward setting=deterministic2025.10 | 3,411 | |
| Offline ML-IRLreward setting=deterministic2025.10 | 3,347 | |
| BCreward setting=deterministic2025.10 | 3,236 | |
| ValueDICEreward setting=deterministic2025.10 | 3,073 |