List your company

Worst-case time-constrained reinforcement learning on Agg. Average across environments (test)

3.07Worst-case RewardOracle-TC-M2TD3
-1.01720.04391.1052.1661Jun 12, 2024

Evaluation results

MethodLinks
Oracle-TC-M2TD3Oracle=true, Framework=TC2024.063.07
TC-M2TD3Framework=TC2024.062.9
Oracle-TC-RARLOracle=true, Framework=TC2024.062.54
Stacked-TC-M2TD3Architecture=Stacked, Framework=TC2024.062.1
Stacked-TC-RARLArchitecture=Stacked, Framework=TC2024.061.78
DRFramework=Domain Randomization2024.061.47
TC-RARLFramework=TC2024.061.46
Oracle M2TD3Oracle=true2024.061.39
M2TD3Framework=Robust2024.061
TD3Framework=Vanilla2024.060
RARLFramework=Robust2024.06-0.08
Oracle RARLOracle=true2024.06-0.86