Ошибка получения: ValueError: слишком много значений для распаковки (ожидается 5) ⇐ Python

[Anonymous]

Код: Выделить всё

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 = self._build_model()

def _build_model(self):

model = Sequential()

model.add(Dense(24, input_dim = self.state_size, activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(24,activation='relu'))
model.add(Dense(50,activation='relu'))

model.add(Dense(self.action_size, activation='sigmoid'))
model.compile(loss='mse', optimizer=Adam(lr=self._learning_rate))

return model

def remember(self, state, action, reward, next_state, done):
self.memory.append((self, state, action, reward, next_state, done))

def act(self, state):
if np.random.rand()  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)

agent = DQNAgent(state_size, action_size)

done = False

for e in range(n_episodes):
state = env.reset()
state = np.reshape(state, [1, state_size])
if agent.epsilon > agent.epsilon_min:
agent.epsilon *= agent.epsilon_decay

for time in range(5000):

# 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, n_episodes, time, agent.epsilon))
break

if len(agent.memory) >  batch_size:

agent.replay(batch_size)

if e % 50 == 0:
agent.save(output_dir + "weights_" + '{:04d}'.format(e) + ".hdf5")

Я создаю алгоритм для среды карт-поля в тренажерном зале Openai, но получаю следующую ошибку:

Traceback (последний последний вызов):
Файл «C:/Users/ardao/Desktop/Ardaficial Intelligence/DQNs/CartPole.py», строка 145, в
Agent.replay(batch_size)
Файл «C:/Users/ardao/Desktop/Ardaficial Intelligence/DQNs/CartPole.py», строка 93, в воспроизведении
для состояния, действия, вознаграждения, next_state, выполненного в мини-пакете:
ValueError: слишком много значений для распаковки (ожидается 5)

Я следую этому руководству:

Спасибо

Арда

Подробнее здесь: https://stackoverflow.com/questions/529 ... expected-5