ResearchBenchmarksReinforcement Learning on Atari-57 (easy settings)Reinforcement Learning on Atari-57 (easy settings)Follow311Median Human-Normalized ScoreDNA219.48243.24267290.76Jun 20, 2022Evaluation resultsMethodMethodLinksMedian Human-Normalized ScoreDNAparameters=2xparameters=2x2022.06311PPOparameters=2xparameters=2x2022.06224Rainbow2022.06223