小编Ard*_*den的帖子

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
import os


env = gym.make('CartPole-v0')
state_size = env.observation_space.shape[0]

action_size = env.action_space.n


batch_size = 32

n_episodes = 1000

output_dir = 'model_output/cartpole'

if not os.path.exists(output_dir):
     os.makedirs(output_dir)


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 = 0.9
        self.epsilon = 1.0
        self.epsilon_decay = 0.995
        self.epsilon_min = 0.05

        self._learning_rate = 0.01

        self.model = …