Inverse Reinforcement Learning on D4RL Walker2d medium-expert
5,384ReturnExpert
Evaluation results
| Method | Links | |
|---|---|---|
| Expertreward setting=deterministic2025.10 | 5,384 | |
| DistIRLreward setting=deterministic2025.10 | 4,570 | |
| Offline ML-IRLreward setting=deterministic2025.10 | 4,201 | |
| ValueDICEreward setting=deterministic2025.10 | 3,191 | |
| BCreward setting=deterministic2025.10 | 2,822 |