List your company

Reinforcement Learning on Pendulum (Efficiency Metrics)

1,000Average DecisionsTD3
24.8024277.9787531.155784.3313May 30, 2023

Evaluation results

MethodLinks
TD32023.051,000121.9
TempoRL2023.05532.57131.01
TD32023.0520024.3
TempoRL2023.05139.3934.14
TLA2023.05111.7926.05
TLA2023.0562.3112.42