Lab 4: Q-learning (table) exploit&exploration and discounted reward code (1)

김성훈 교수님의 Reinforcement Learning 강의 lab4의 add random noise가 적용된 Q-learning 실습 예제를 구현한 소스입니다.

강의가 필요하신 분을 위해 link 남겨드립니다.

https://www.youtube.com/watch?v=VYOq-He90bE&index=7&list=PLlMkM4tgfjnKsCWav-Z2F-MMFRx-2gMGG

import gym
import numpy as np
import matplotlib.pyplot as plt
from gym.envs.registration import register
 
register(
    id='FrozenLake-v3',
    entry_point='gym.envs.toy_text:FrozenLakeEnv',
    kwargs={'map_name': '4x4',
            'is_slippery': False}
)
 
env = gym.make('FrozenLake-v3')
 
Q = np.zeros([env.observation_space.n, env.action_space.n])
dis = .99
num_episodes = 2000
rList = []
 
for i in range(num_episodes):
    state = env.reset()
    rAll = 0
    done = False
 
    while not done:
        action = np.argmax(Q[state, :] + np.random.randn(1, env.action_space.n) / (i + 1))
        new_state, reward, done,_ = env.step(action)
 
        Q[state,action] = reward + dis * np.max(Q[new_state,:])
 
        rAll += reward
        state = new_state
 
    rList.append(rAll)
 
print("Success rate: " + str(sum(rList)/num_episodes))
print("Final Q-Table Values")
print(Q)
plt.bar(range(len(rList)), rList, color="blue")
plt.show()