Reinforcement Learning on Ant fixed linear adversary
8,069Average PerformanceTC-RARL
Evaluation results
| Method | Links | |
|---|---|---|
| TC-RARLOracle=true2024.06 | 8,069 | |
| TC-M2TD3Oracle=true2024.06 | 7,919 | |
| DR2024.06 | 7,713 | |
| TC-RARLStacked=false, Oracle=false2024.06 | 7,675 | |
| TC-M2TD3Stacked=false, Oracle=false2024.06 | 7,622 | |
| TC-RARLStacked=true2024.06 | 7,328 | |
| TC-M2TD3Stacked=true2024.06 | 7,003 | |
| M2TD3Oracle=true2024.06 | 5,811 | |
| M2TD32024.06 | 5,444 | |
| RARL2024.06 | 4,651 | |
| RARLOracle=true2024.06 | 4,447 | |
| TD32024.06 | 3,493 |