Value Iteration
In a 10×10 grid world, do 30 times value iteration.
Requirements:
1. A 10×10 grid world
2. Noise=0.15, discount = 0.91
3. There are four actions west, east, north, south. The actionsare all “north” in the initial policy. After each iteration, theactions in the policy need to be updated to the direction thatpoints to the adjacent grid that has the highest value.
4. There are two terminal grids, one has reward +2 and the otherone is -2. The location should be given set by using the givenvariables at the beginning.
5. One grid is occupied by a stone whose location is specifiedby the giving variables
OR
OR