List your company
ResearchFormerly WizWand

Continuous Control on OpenAI Gym MuJoCo Pendulum POMDP (test)

174Average ReturnPolyGRAD
158.816162.758166.7170.642Jun 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
PolyGRADObservation Type=Partial2024.06174
Dreamer-v2Observation Type=Partial2024.06172.3
µLV-RepObservation Type=Partial2024.06168.2
Diff-SRObservation Type=Partial2024.06167.4
SLACObservation Type=Partial2024.06167.3
SAC-MLPObservation Type=Partial2024.06163.6
Diff-SRObservation Type=Full2024.06162.3
PSRObservation Type=Partial2024.06159.4