List your company

Policy Evaluation on 400-State Random MDP off-policy (Sum of sqrt MSE)

29.65Sum of sqrt MSEBBO
13.1176124.7113236.305347.8987Jun 9, 2021

Evaluation results

MethodLinks
BBOPolicy Type=off-policy2021.0629.65
LSTD+Policy Type=off-policy2021.0629.65
BRMPolicy Type=off-policy2021.0632.13
TDPolicy Type=off-policy2021.06113.3
TDCPolicy Type=off-policy2021.06266.36
GTD2Policy Type=off-policy2021.06442.96