ResearchBenchmarksReinforcement Learning on Atari 2600 Q*bertReinforcement Learning on Atari 2600 Q*bertFollow11,931Mean ScoreRainbow-322.282,858.866,0409,221.14Feb 18, 2021Evaluation resultsMethodMethodLinksMean ScoreMax ScoreRainbowPlasticity=full, Activ...Plasticity=full, Activation=rational2021.0211,93123,550RainbowPlasticity=regularised...Plasticity=regularised, Activation=joint-rational2021.0211,55123,550RainbowPlasticity=rigid, Acti...Plasticity=rigid, Activation=Leaky ReLU2021.0214916,125