List your company
ResearchFormerly WizWand

Reinforcement Learning on Delayed MuJoCo HalfCheetah v2 (test)

8,451.2Average ReturnDE-MME
3,905.84885,085.89196,265.9357,445.9781Jun 19, 2021
Updated 8mo ago

Evaluation results

MethodLinks
DE-MME2021.068,451.2
MaxEnt(State)2021.067,907.98
DAC2021.067,594.7
RND2021.067,429.94
MME2021.067,299.28
SAC-Div2021.064,080.67