TD Prediction

The algorithm for the TD prediction method is given as follows:

1. Initialize the value function V(s) with random values. A policy is given.
2. For each episode:
   1. Initialize the state s
   2. For each step in the episode:
      1. Perform an action a in the state s according to given policy , get the reward r, and move to the next state
      2. Update the value of the state to
      3. Update (this step implies we are changing the next state to the current state s)
      4. If s is not a terminal state, repeat steps 1 to 4