2D bipedal locomotion on PitGap (test)
143.2Average ReturnADD
Evaluation Results
| Method | Links | |
|---|---|---|
| ADDTraining Algorithm=PPO, Environmental Steps=2 billion, Guidance=true2024.10 | 143.2 | |
| PLRTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | 54.2 | |
| ACCELTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | 29.6 | |
| ADDTraining Algorithm=PPO, Environmental Steps=2 billion, Guidance=false2024.10 | 6.7 | |
| DRTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | -1.8 | |
| PAIREDTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | -68.2 |