2D bipedal locomotion on Basic (OpenAI Gym) (test)
312Average ReturnADD
Evaluation Results
| Method | Links | |
|---|---|---|
| ADDTraining Algorithm=PPO, Environmental Steps=2 billion, Guidance=true2024.10 | 312 | |
| PLRTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | 306 | |
| ADDTraining Algorithm=PPO, Environmental Steps=2 billion, Guidance=false2024.10 | 280.8 | |
| ACCELTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | 252 | |
| PAIREDTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | 206.5 | |
| DRTraining Algorithm=PPO, Environmental Steps=2 billion2024.10 | 153.7 |