DQN实战(三)——CartPole(keras)

使用OpenAI-Gym中的CartPole

tensorflow1.13.1

keras2.2.4

 

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

from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten
from keras.optimizers import Adam

from rl.agents.dqn import DQNAgent
from rl.policy import EpsGreedyQPolicy
from rl.memory import SequentialMemory

#初始化gym
ENV_NAME = 'CartPole-v0'

# Get the environment and extract the number of actions.
env = gym.make(ENV_NAME)

nb_actions = env.action_space.n

#Keras搭建深度神经网络
model = Sequential()
model.add(Flatten(input_shape=(1,) + env.observation_space.shape))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(nb_actions))
model.add(Activation('linear'))
print(model.summary())


#配置智能体
memory = SequentialMemory(limit=50000, window_length=1)
policy = EpsGreedyQPolicy()
dqn = DQNAgent(model=model, nb_actions=nb_actions, memory=memory, nb_steps_warmup=10,
               target_model_update=1e-2, policy=policy)
dqn.compile(Adam(lr=1e-3), metrics=['mae'])

#训练和验证

H = dqn.fit(env, nb_steps=10000, visualize=False, verbose=2)

dqn.test(env, nb_episodes=5, visualize=True)

 

 

 

参考

https://www.jianshu.com/p/cc5b995cf8db