List your company
ResearchFormerly WizWand

Continuous Control on MuJoCo HalfCheetah fixed random adversary L=0.1

8,805Average ReturnOracle TC-M2TD3
-405.241,985.884,3776,768.12Jun 12, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Oracle TC-M2TD3Oracle=true, Time-Constrained=true2024.068,805
Oracle TC-RARLOracle=true, Time-Constrained=true2024.068,727
TC-M2TD3Time-Constrained=true2024.067,530
Stacked TC-M2TD3Stacked=true, Time-Constrained=true2024.067,400
DR2024.066,048
Stacked TC-RARLStacked=true, Time-Constrained=true2024.065,992
TC-RARLTime-Constrained=true2024.065,751
Oracle M2TD3Oracle=true2024.064,445
M2TD32024.064,180
TD32024.062,028
RARL2024.06240
Oracle RARLOracle=true2024.06-51