ResearchBenchmarksReinforcement Learning on Inv-DPendulumFollow1,000DecisionsTD3217.6704420.7752623.88826.9848May 30, 2023Evaluation ResultsMethodMethodLinksDecisionsAvg MMACsTD32023.051,000124.7TempoRL2023.05850.95213.59TLA2023.05247.7657.46