ResearchBenchmarksReinforcement Learning on SixArmsReinforcement Learning on SixArmsFollow9.3Cumulative RewardMBIE1.53.5255.557.575Jul 31, 2018Evaluation resultsMethodMethodLinksCumulative RewardMBIEScale=millionsScale=millions2018.079.3ESSRScale=millions, Runs=100Scale=millions, Runs=1002018.077.3R-MAXScale=millionsScale=millions2018.072.8E3Scale=millionsScale=millions2018.071.8