List your company
ResearchFormerly WizWand

Continuous Control on OpenAI Gym MuJoCo Humanoid POMDP (test)

823.1Average ReturnDiff-SR
218.86375.73532.6689.47Jun 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Diff-SRObservation Type=Full2024.06823.1
µLV-RepObservation Type=Partial2024.06806.7
PolyGRADObservation Type=Partial2024.06764.5
Dreamer-v2Observation Type=Partial2024.06672.5
Diff-SRObservation Type=Partial2024.06650.1
PSRObservation Type=Partial2024.06534.4
SLACObservation Type=Partial2024.06387.4
SAC-MLPObservation Type=Partial2024.06242.1