dharma6872

colbab 텐서플로우 버전 변경, runtime restart 필요

%tensorflow_version 1.x

colbab 텐서플로우 버전 확인

import tensorflow
print(tensorflow.__version__)

dharma6872

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


"""Lecture 4 Q learning"""

import gym
import numpy as np
import random
import matplotlib.pyplot as plt
from gym.envs.registration import register

dharma6872

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

"""Lecture 3 Dummy Q-learning (table)"""


import numpy as np
import gym
from gym.envs.registration import register
import random as pr
import matplotlib.pyplot as plt

dharma6872

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

"""Lecture 5 Q learning Nondeterministic"""



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

dharma6872

reshape 함수

import tensorflow as tf
import numpy as np

x = [i for i in range(10)]
print(x)

y = tf.reshape(x, shape=[-1, 5])
print(y)

dharma6872

import logging
import logging.handlers

log = logging.getLogger('snowdeer_log')
log.setLevel(logging.DEBUG)

formatter = logging.Formatter('[%(levelname)s] (%(filename)s:%(lineno)d) > %(message)s')

fileHandler = logging.FileHandler('./log.txt')
streamHandler = logging.StreamHandler()

dharma6872

import numpy as np

state_rewards = [-5, 0, 0, 0, 0, 0, 5]
final_state = [True, False, False, False, False, False, True]

Q_values = [[0.0, 0.0],
			[0.0, 0.0],
			[0.0, 0.0],
			[0.0, 0.0],
			[0.0, 0.0],

dharma6872

import numpy as np

# action 별 reward 반환 함수
def pull_bandit_arm(bandits, bandit_number):
	# Pull arm in position bandit_number and return the obtained reward.
	result = np.random.uniform()
	return int(result <= bandits[bandit_number]) # 0 또는 1을 반환한다.

# action 을 결정하는 함수
# 탐험률 반영

dharma6872

import gym
import random
import numpy as np
from keras.layers import Dense, Flatten
from keras.models import Sequential
from keras.optimizers import Adam

env = gym.make('CartPole-v1')

states = env.observation_space.shape[0]

dharma6872

import gym
import numpy as np
import random
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import Adam

from collections import deque

class DQN: