Robot Locomotion on Humanoid
5,299Cumulative RewardPPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PPO2023.10 | 5,299 | — | |
| DIPG2023.10 | 5,191 | 0.12 | |
| DvD2023.10 | 4,498 | 0.4 | |
| SMERL2023.10 | 4,253 | 0.01 | |
| SIPO-WD2023.10 | 3,763 | 0.71 | |
| SIPO-RBF2023.10 | 3,508 | 0.53 | |
| RSPO2023.10 | 1,455 | 0.53 | |
| CT-SACHyperparameter Rank=top2026.02 | 386.75 | — | |
| CT-SACHyperparameter Rank=second2026.02 | 379.75 | — | |
| CT-SACHyperparameter Rank=third2026.02 | 371.75 | — | |
| TRPOHyperparameter Rank=top2026.02 | 1.39 | — | |
| TRPOHyperparameter Rank=second2026.02 | 1.33 | — | |
| TRPOHyperparameter Rank=third2026.02 | 1.3 | — | |
| PPOHyperparameter Rank=top2026.02 | 1.18 | — | |
| PPOHyperparameter Rank=second2026.02 | 1.17 | — | |
| PPOHyperparameter Rank=third2026.02 | 1.11 | — | |
| DIPGPopulation size=42023.10 | — | 0.12 | |
| DvDPopulation size=42023.10 | — | 0.4 | |
| RSPOPopulation size=42023.10 | — | 0.53 | |
| SIPO-RBFPopulation size=42023.10 | — | 0.53 | |
| SIPO-WDPopulation size=42023.10 | — | 0.71 | |
| SMERLPopulation size=42023.10 | — | 0.01 |