List your company

Continuous Control on reacher3da RandomTarget

0.467Average RewardDDPG
-0.066520.071990.21050.34901Sep 9, 2015

Evaluation results

MethodLinks
DDPGObservation Space=low-dimensional2015.090.4670.739
DDPGObservation Space=pixels2015.090.3740.735
DPGSetup=original with replay buffer and batch normalization2015.09-0.0460.158