Lecture 3 - Turn Based Stochastic Games

Theorem: For a stopping TBSG:1. The optimality equations have a unique solution.2. ... Can still use value iteration and some form of policy iteration. The Value Iteration Operator. ??(?)is the optimal value vector of an ?-step game with . ......

Author:
Uploaded by: Murkka Svensdottir
Filesize: 1 MB