Example for policy evaluation in a small gridworld problem

The files contain the algorithm to estimate the values of states in finite gridworld using random policy for movements

This small problem solution corresponds to Example 4.1 from the book:

"Reinforcement Learning An Introduction"

second edition

by Richard S. Sutton and Andrew G. Barto

ISBN: 978-0-262-19398-6

The code estimates the value of a starting point grid, using randomly selected actions-movements until the exit grid is reached