List your company

Reinforcement Learning on Atari Beam Rider

188,200Mean ReturnR2D2
10,04856,299102,550148,801Feb 14, 2020

Evaluation results

MethodLinks
R2D22020.02188,200
NGUN=1, Variant=without RND2020.02166,500
NGUN=12020.02114,600
R2D2Loss=Retrace2020.02111,100
R2D2Extension=RND2020.0285,700
NGUN=322020.0268,700
Human2020.0216,900