ResearchBenchmarksReinforcement Learning on Pendulum (Efficiency Metrics)Follow1,000Average DecisionsTD324.8024277.9787531.155784.3313May 30, 2023Evaluation ResultsMethodMethodLinksAverage DecisionsAverage MMACsTD32023.051,000121.9TempoRL2023.05532.57131.01TD32023.0520024.3TempoRL2023.05139.3934.14TLA2023.05111.7926.05TLA2023.0562.3112.42