Inverse Reinforcement Learning on D4RL HalfCheetah
3,540ReturnExpert
Evaluation Results
| Method | Links | |
|---|---|---|
| Expert2025.10 | 3,540 | |
| DistIRL2025.10 | 3,469 | |
| DistIRL-qrt2025.10 | 3,294 | |
| BC2025.10 | 2,828 | |
| ValueDICE2025.10 | 1,259 | |
| Offline ML-IRL2025.10 | 826 |
Loading the SOTA2 catalog…