List your company

Continuous Control on pendulum

0.946Average RewardDDPG
0.065120.293810.52250.75119Sep 9, 2015

Evaluation results

MethodLinks
DDPGObservation Space=low-dimensional2015.090.9461.021
DDPGObservation Space=pixels2015.090.6631.055
DPGSetup=original with replay buffer and batch normalization2015.090.0990.951