ResearchBenchmarksPolicy Evaluation on 400-State Random MDP off-policy (Sum of sqrt MSE)Follow29.65Sum of sqrt MSEBBO13.1176124.7113236.305347.8987Jun 9, 2021Evaluation ResultsMethodMethodLinksSum of sqrt MSEBBOPolicy Type=off-policyPolicy Type=off-policy2021.0629.65LSTD+Policy Type=off-policyPolicy Type=off-policy2021.0629.65BRMPolicy Type=off-policyPolicy Type=off-policy2021.0632.13TDPolicy Type=off-policyPolicy Type=off-policy2021.06113.3TDCPolicy Type=off-policyPolicy Type=off-policy2021.06266.36GTD2Policy Type=off-policyPolicy Type=off-policy2021.06442.96