Reinforcement Learning on Humanoid v5 (Average Returns)
5,228Average ReturnsSAC - H-EARS
Evaluation results
| Method | Links | |
|---|---|---|
| SAC - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=SAC2026.03 | 5,228 | |
| TD3 - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=TD32026.03 | 5,190 | |
| SAC - VanillaAlgorithm Variant=Vanilla, Base Algorithm=SAC2026.03 | 4,988 | |
| TD3 - VanillaAlgorithm Variant=Vanilla, Base Algorithm=TD32026.03 | 4,964 | |
| DDPG - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=DDPG2026.03 | 1,620 | |
| DDPG - VanillaAlgorithm Variant=Vanilla, Base Algorithm=DDPG2026.03 | 1,524 | |
| PPO - VanillaAlgorithm Variant=Vanilla, Base Algorithm=PPO2026.03 | 197 | |
| PPO - H-EARSAlgorithm Variant=H-EARS, Base Algorithm=PPO2026.03 | 178 |