# -*- coding: utf-8 -*-
import random
import gym
import numpy as np
from collections import deque
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam
from keras.utils.vis_utils import plot_modelEPISODES = 1000class DQNAgent:def __init__(self, state_size, action_size):self.state_size = state_sizeself.action_size = action_sizeself.memory = deque(maxlen=2000)self.gamma = 0.95    # discount rate#self.epsilon = 1.0  # exploration rateself.epsilon = 0.4  # exploration rateself.epsilon_min = 0.01self.epsilon_decay = 0.995self.learning_rate = 0.001self.model = self._build_model()#可视化MLP结构plot_model(self.model, to_file='dqn-cartpole-v0-mlp.png', show_shapes=False)def _build_model(self):# Neural Net for Deep-Q learning Modelmodel = Sequential()model.add(Dense(24, input_dim=self.state_size, activation='relu'))model.add(Dense(24, activation='relu'))model.add(Dense(self.action_size, activation='linear'))model.compile(loss='mse',optimizer=Adam(lr=self.learning_rate))return modeldef remember(self, state, action, reward, next_state, done):self.memory.append((state, action, reward, next_state, done))def act(self, state):if np.random.rand() <= self.epsilon:return random.randrange(self.action_size)act_values = self.model.predict(state)#print("act_values:")#print(act_values)return np.argmax(act_values[0])  # returns actiondef replay(self, batch_size):minibatch = random.sample(self.memory, batch_size)for state, action, reward, next_state, done in minibatch:target = rewardif not done:target = (reward + self.gamma *np.amax(self.model.predict(next_state)[0]))target_f = self.model.predict(state)target_f[0][action] = targetself.model.fit(state, target_f, epochs=1, verbose=0)#if self.epsilon > self.epsilon_min:#    self.epsilon *= self.epsilon_decaydef load(self, name):self.model.load_weights(name)def save(self, name):self.model.save_weights(name)if __name__ == "__main__":env = gym.make('CartPole-v0')state_size = env.observation_space.shape[0]action_size = env.action_space.n#print(state_size)#print(action_size)agent = DQNAgent(state_size, action_size)done = Falsebatch_size = 32avg=0for e in range(EPISODES):state = env.reset()state = np.reshape(state, [1, state_size])for time in range(500):env.render()action = agent.act(state)next_state, reward, done, _ = env.step(action)reward = reward if not done else -10next_state = np.reshape(next_state, [1, state_size])agent.remember(state, action, reward, next_state, done)state = next_stateif done:print("episode: {}/{}, score: {}, e: {:.2}".format(e, EPISODES, time, agent.epsilon))avg+=timebreakif len(agent.memory) > batch_size:agent.replay(batch_size)print("Avg score:{}".format(avg/1000))