List your company

Continuous Control on cartpoleSerialTriple

0.736Average RewardDDPG
0.399040.486520.5740.66148Sep 9, 2015

Evaluation results

MethodLinks
DDPGObservation Space=low-dimensional2015.090.7360.946
DPGSetup=original with replay buffer and batch normalization2015.090.5830.942
DDPGObservation Space=pixels2015.090.4120.427