Enhancing Video Games Policy Based on Least-Squares Continuous Action Policy Iteration: Case Study on StarCraft Brood War and Glest RTS Games and the 8 Queens Board Game

Algorithm 1

Offline Least-Squares Continuous Actions Policy Iteration.

Input: discount factor

: , , : ,

() , initialize policy

() measure initial state

() for step do

() ,  ; ,  

() apply , measure state , and reward

() start LSTD- policy evaluation

  , ,

()

()

()

() finalize policy evaluation

() policy improvement

() until is a satisfactory

()

() end for

Output: