ResearchBenchmarksReinforcement Learning on Atari Qbert v4 (test)Reinforcement Learning on Atari Qbert v4 (test)Follow27,234.1Mean Final ScoreSTG-679.1886,567.53113,814.2521,060.969Jun 22, 2023Evaluation resultsMethodMethodLinksMean Final ScoreSTG2023.0627,234.1Expert2023.0615,620.7PPO2023.0614,293.3ELE2023.064,698.6GAIfO2023.06394.4