Inverse Reinforcement Learning on HalfCheetah no disability (Target)
6,420.38Mean Cumulative RewardExpert
Evaluation results
| Method | Links | |
|---|---|---|
| ExpertType=Target, Configuration=no disability2025.01 | 6,420.38 | |
| TraIRLType=Target, Configuration=no disability2025.01 | 5,835.11 | |
| I2LType=Target, Configuration=no disability2025.01 | 4,512.71 | |
| RIMEType=Target, Configuration=no disability2025.01 | 4,061.22 | |
| AIRL-METype=Target, Configuration=no disability2025.01 | 3,725.63 | |
| f-IRLType=Target, Configuration=no disability2025.01 | 3,582.1 |