List your company
ResearchFormerly WizWand

Continuous Control on OpenAI Gym MuJoCo Hopper POMDP (test)

2,800.5Average ReturnDiff-SR
436.8921,050.5211,664.152,277.779Jun 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Diff-SRObservation Type=Full2024.062,800.5
Diff-SRObservation Type=Partial2024.061,357.6
µLV-RepObservation Type=Partial2024.061,096.4
PSRObservation Type=Partial2024.06818.8
Dreamer-v2Observation Type=Partial2024.06758.3
SLACObservation Type=Partial2024.06739.3
SAC-MLPObservation Type=Partial2024.06614.15
PolyGRADObservation Type=Partial2024.06527.8