Inverse Reinforcement Learning on D4RL Walker2d
1,526ReturnDistIRL
Evaluation Results
| Method | Links | |
|---|---|---|
| DistIRL2025.10 | 1,526 | |
| Expert2025.10 | 1,478 | |
| BC2025.10 | 1,321 | |
| DistIRL-qrt2025.10 | 1,211 | |
| ValueDICE2025.10 | 798 | |
| Offline ML-IRL2025.10 | 240 |
Loading the SOTA2 catalog…