List your company
ResearchFormerly WizWand

Reinforcement Learning on HalfCheetah

1,000Average DecisionsTD3
824.6768870.1934915.71961.2266May 30, 2023
Updated 8mo ago

Evaluation results

MethodLinks
TD32023.051,000128.6
TempoRL2023.05889.57230.13
TLA2023.05831.42182.35