DQN 处理 CartPole 问题——使用强化学习，本质上是训练MLP，预测每一个动作的得分

Posted 2020-11-11 将者，智、信、仁、勇、严也。

代码：

# -*- 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_model

EPISODES = 1000


class DQNAgent:
    def __init__(self, state_size, action_size):
        self.state_size = state_size
        self.action_size = action_size
        self.memory = deque(maxlen=2000)
        self.gamma = 0.95    # discount rate
        #self.epsilon = 1.0  # exploration rate
        self.epsilon = 0.4  # exploration rate
        self.epsilon_min = 0.01
        self.epsilon_decay = 0.995
        self.learning_rate = 0.001
        self.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 Model
        model = 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 model

    def 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 action

    def replay(self, batch_size):
        minibatch = random.sample(self.memory, batch_size)
        for state, action, reward, next_state, done in minibatch:
            target = reward
            if not done:
                target = (reward + self.gamma *
                          np.amax(self.model.predict(next_state)[0]))
            target_f = self.model.predict(state)
            target_f[0][action] = target
            self.model.fit(state, target_f, epochs=1, verbose=0)
        #if self.epsilon > self.epsilon_min:
        #    self.epsilon *= self.epsilon_decay

    def 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 = False
    batch_size = 32
    avg=0

    for 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 -10
            next_state = np.reshape(next_state, [1, state_size])
            agent.remember(state, action, reward, next_state, done)
            state = next_state
            if done:
                print("episode: {}/{}, score: {}, e: {:.2}"
                      .format(e, EPISODES, time, agent.epsilon))
                avg+=time
                break
        if len(agent.memory) > batch_size:
            agent.replay(batch_size)

    print("Avg score:{}".format(avg/1000))

 基本思路：

让他自己训练玩这个游戏（每次应该左右移动的距离），基本思路就是：

本质上就是使用MLP训练（动作，得分）

这个得分是坚持时间的长短，如果时间长得分就高。

但是我感觉这个gym自己做了很多事情，比如度量奖励分数，action描述等。待进一步挖掘！