List your company

Continuous Control on cartpoleSerialDouble

0.272Average RewardDDPG
0.137840.172670.20750.24233Sep 9, 2015

Evaluation results

MethodLinks
DDPGObservation Space=low-dimensional2015.090.2720.719
DDPGObservation Space=pixels2015.090.1950.642
DPGSetup=original with replay buffer and batch normalization2015.090.1430.701