Robust Reinforcement Learning on HumanoidStandup fixed exponential adversary MuJoCo
129,966Avg PerformanceTC-M2TD3
Evaluation results
| Method | Links | |
|---|---|---|
| TC-M2TD32024.06 | 129,966 | |
| M2TD3Oracle=true2024.06 | 119,205 | |
| TC-M2TD3Oracle=true2024.06 | 118,476 | |
| TC-RARLOracle=true2024.06 | 110,092 | |
| M2TD32024.06 | 107,097 | |
| TC-RARL2024.06 | 106,491 | |
| DR2024.06 | 106,290 | |
| TC-RARLStacked=true2024.06 | 104,793 | |
| RARL2024.06 | 102,096 | |
| TC-M2TD3Stacked=true2024.06 | 91,077 | |
| TD32024.06 | 90,496 | |
| RARLOracle=true2024.06 | 82,063 |