[Lecture 5 Q learning Nondeterministic] #강화학습

Lecture 5 Q learning Nondeterministic.py

# -*- coding: utf-8 -*-

"""Lecture 5 Q learning Nondeterministic"""



import numpy as np
import gym
import random
import matplotlib.pyplot as plt



env = gym.make("FrozenLake-v0")

Q = np.zeros([env.observation_space.n, env.action_space.n])

learning_rate = .85
dis = .99
num_episodes = 2000



"""### 미끄러지는 환경에서 학습"""


rList = []
for i in range(num_episodes):
	state = env.reset()
	rAll = 0
	done = False

	while not done:
		action = np.argmax(Q[state, :] + np.random.rand(1, env.action_space.n) / (i + 1))
		new_state, reward, done, _ = env.step(action)
		Q[state, action] = reward + dis * np.max(Q[new_state, :])
		state = new_state

		rAll += reward

	rList.append(rAll)

print("Score over time: " + str(sum(rList) / num_episodes))
print("Final Q-table Value")
print(Q)
plt.bar(range(len(rList)), rList, color="blue")
plt.show()



"""### 미끄러지는 경우 반영"""


rList = []
for i in range(num_episodes):
	state = env.reset()
	rAll = 0
	done = False

	while not done:
		action = np.argmax(Q[state, :] + np.random.rand(1, env.action_space.n) / (i + 1))
		new_state, reward, done, _ = env.step(action)
		#Q[state, action] = reward + dis * np.max(Q[new_state, :])
		Q[state, action] = (1- learning_rate) * Q[state, action] + \
								learning_rate * (reward + dis * np.max(Q[new_state, :]))        
		state = new_state

		rAll += reward

	rList.append(rAll)

print("Score over time: " + str(sum(rList) / num_episodes))
print("Final Q-table Value")
print(Q)
plt.bar(range(len(rList)), rList, color="blue")
plt.show()