Reinforcement-Learning-Golang

In this repository I'll be programming the cool exercises of the Book Reinforcement-Learning: An introduction by Sutton

Jacks-car-rental-with-policy-iteration

Solution to the Exercise 4.5 of the book Reinforcement Learning by Sutton

example output 5x5

0 0 1 1 2 2
0 0 0 1 1 2
1 1 0 0 1 1
2 1 1 0 0 1
2 2 1 1 0 0
3 2 2 1 0 0

gambler-problem-value-iteration

solution to the problem 4.9 of the book Reinforcement Learning by Sutton

using probability = 0.25

using probability = 0.45

using probability = 0.55

Windy Gridworld

Solution to the Example 6.5 of the book Reinforcement Learning by Sutton
Output 4 actions:

Output 8 actions:

Output 9 actions:

Output stochastic:

Cliff Walking

Solution to the Example 6.6 of the book Reinforcement Learning by Sutton Output

Mountain Car using Sarsa with semi-gradient and coarse coding.