# For practice purpose as part of Reinforcement Learning course.

## Optimized policy via Genetic Algorithm
best_policy = [3, 2, 3, 2, 3, 2, 2, 0, 3, 3, 3, 3, 2, 3, 2, 1, 2, 2, 0, 2, 2, 2, 2, 2, 0, 3, 1, 1, 0, 2, 2, 2, 0, 3, 3, 0, 2, 1, 3, 2, 1, 2, 0, 0, 1, 0, 3, 2, 2, 0, 0, 0, 3, 2, 0, 2, 0, 1, 2, 1, 3, 3, 0, 0]
import gym
from gym import wrappers
env = gym.make('FrozenLake8x8-v0')
env = wrappers.Monitor(env, '/tmp/frozenlake-experiment-2')
for i_episode in range(4000):
    observation = env.reset()
    for t in range(400):
        env.render()
        observation, reward, done, info = env.step(best_policy[observation])
        if done:
            print("Episode finished after {} timesteps".format(t+1))
            break
env.close()