List your company

Continuous Control on InvertedDoublePendulum v1 (train)

9,355.52Max Average ReturnDDPG
-160.13682,310.27414,780.6857,251.0959Feb 26, 2018

Evaluation results

MethodLinks
DDPG2018.029,355.52
TD32018.029,337.47
ACKTR2018.029,081.92
PPO2018.028,977.94
SAC2018.028,487.15
Our DDPG2018.028,369.95
TRPO2018.02205.85