List your company
ResearchFormerly WizWand

Multi-task Reinforcement Learning on Atari-57 clipped

110.7Median Human Normalized ScorePopArt-IMPALA
25.21247.40669.691.794Sep 12, 2018
Updated 8mo ago

Evaluation results

MethodLinks
PopArt-IMPALAEvaluation Start Type=Random2018.09110.7
PopArt-IMPALAEvaluation Start Type=Human2018.09101.5
IMPALAEvaluation Start Type=Random2018.0959.7
IMPALAEvaluation Start Type=Human2018.0928.5