Reinforcement Learning on HumanoidStandup fixed linear adversary
129,501Average PerformanceTC-M2TD3
Evaluation results
| Method | Links | |
|---|---|---|
| TC-M2TD32024.06 | 129,501 | |
| M2TD3Oracle=true2024.06 | 118,829 | |
| TC-M2TD3Oracle=true2024.06 | 117,610 | |
| TC-RARLOracle=true2024.06 | 110,314 | |
| DR2024.06 | 108,711 | |
| M2TD32024.06 | 106,311 | |
| TC-RARL2024.06 | 105,566 | |
| TC-RARLStacked=true2024.06 | 105,137 | |
| RARL2024.06 | 101,477 | |
| TD32024.06 | 89,934 | |
| TC-M2TD3Stacked=true2024.06 | 89,556 | |
| RARLOracle=true2024.06 | 81,498 |