Maze Solver (Reinforcement Learning)

Refer to 4.1, Reinforcement learning: An introduction, RS Sutton, AG Barto , MIT press
Value Iterations:
Algorithms of dynamic programming to solve finite MDPs. Policy evaluation refers to the (typically) iterative computation of the value functions for a given policy. Policy improvement refers to the computation of an improved policy given the value function for that policy. Putting these two computations together, we obtain policy iteration and value iteration, the two most popular DP methods. Either of these can be used to reliably compute optimal policies and value functions for finite MDPs given complete knowledge of the MDP.

◮ Problem: find optimal policy π
◮ Solution: iterative application of Bellman optimality backup
◮ v1 → v2 → ... → v∗
◮ Using synchronous backups, At each iteration k + 1 For all states s ∈ S : Update v_{k+1}(s) from v_{k}(s')
◮ Convergence to v∗ will be proven later
◮ Unlike policy iteration, there is no explicit policy
◮ Intermediate value functions may not correspond to any policy