43207fd5e34f87c48d584fc5c11befb8-Supplemental.pdf

Is Plug-in Solver Sample Efficient for Feature-based Reinfocement Learning? DMDP, so the optimal policy exists for player 1. For this policy, neither player can benefit from change its policy alone. We give the following well-known properties of 2-TBSG without proof (see. Here we prove the three arguments in Proposition 1. 1.