Inverse Reinforcement Learning on D4RL HalfCheetah medium-expert
12,175ReturnExpert
Evaluation results
| Method | Links | |
|---|---|---|
| Expertreward setting=deterministic2025.10 | 12,175 | |
| DistIRLreward setting=deterministic, data amount=same as Offline ML-IRL2025.10 | 11,239 | |
| Offline ML-IRLreward setting=deterministic2025.10 | 11,231 | |
| DistIRLreward setting=deterministic2025.10 | 7,779 | |
| ValueDICEreward setting=deterministic2025.10 | 4,935 | |
| BCreward setting=deterministic2025.10 | 623 |