List your company

Policy Evaluation on 20-Link Pole off-policy (Sum of sqrt MSE)

415.37Sum of sqrt MSEBBO
399.8068504.8584609.91714.9616Jun 9, 2021

Evaluation results

MethodLinks
BBOPolicy Type=off-policy2021.06415.37
LSTD+Policy Type=off-policy2021.06421.74
TDPolicy Type=off-policy2021.06470.12
TDCPolicy Type=off-policy2021.06470.2
BRMPolicy Type=off-policy2021.06768.59
GTD2Policy Type=off-policy2021.06802.78
LSTDPolicy Type=off-policy2021.06804.45