Value-Iteration Algorithm:
For each iteration k+1:
a. calculate the optimal state-value function for all s∈S;
b. untill algorithm converges.
end up with an optimal state-value function
Optimal State-Value Function
As mentioned on the previous post, the method to pick up Optimal State-Value Function is shown below. From state s, we have multiple possible actions, what we will do is choose the best combination of immediate reward and state-value function from the next state.
Example for a grid game, it is quite like information propagate from the terminal states backward:
From State-Value Function to Policy
After we‘ve got the Optimal State-Value Function, the Optimal Policy can be aquired by maxmizing the Action-Value Function. This means we try all possible actions from state s, and then choose the one that has the maximum reward.
Value Iteration Algorithm for MDP
原文：https://www.cnblogs.com/rhyswang/p/11206150.html