Worst-case time-constrained reinforcement learning on Agg. Average across environments (test)
3.07Worst-case RewardOracle-TC-M2TD3
Evaluation Results
| Method | Links | |
|---|---|---|
| Oracle-TC-M2TD3Oracle=true, Framework=TC2024.06 | 3.07 | |
| TC-M2TD3Framework=TC2024.06 | 2.9 | |
| Oracle-TC-RARLOracle=true, Framework=TC2024.06 | 2.54 | |
| Stacked-TC-M2TD3Architecture=Stacked, Framework=TC2024.06 | 2.1 | |
| Stacked-TC-RARLArchitecture=Stacked, Framework=TC2024.06 | 1.78 | |
| DRFramework=Domain Randomization2024.06 | 1.47 | |
| TC-RARLFramework=TC2024.06 | 1.46 | |
| Oracle M2TD3Oracle=true2024.06 | 1.39 | |
| M2TD3Framework=Robust2024.06 | 1 | |
| TD3Framework=Vanilla2024.06 | 0 | |
| RARLFramework=Robust2024.06 | -0.08 | |
| Oracle RARLOracle=true2024.06 | -0.86 |