ResearchBenchmarksPolicy Evaluation on 400-State Random MDP on-policy (Sum of sqrt MSE)Follow24.74Sum of sqrt MSEBBO12.027297.8386183.65269.4614Jun 9, 2021Evaluation ResultsMethodMethodLinksSum of sqrt MSEBBOPolicy Type=on-policyPolicy Type=on-policy2021.0624.74LSTD+Policy Type=on-policyPolicy Type=on-policy2021.0624.74LSTDPolicy Type=on-policyPolicy Type=on-policy2021.0627.75BRMPolicy Type=on-policyPolicy Type=on-policy2021.0627.87TDCPolicy Type=on-policyPolicy Type=on-policy2021.06119.84TDPolicy Type=on-policyPolicy Type=on-policy2021.06122.51GTD2Policy Type=on-policyPolicy Type=on-policy2021.06342.56