我正在尝试使用tensorflow在Python中编写DQN。要使用GPU，我正在google colab中运行我的代码。我写了自己的环境，代理商可以在4个动作之间进行选择，以订购特定数量的补给他的仓库。 运行DQN时，出现以下错误：
尝试共享变量eval_net / e1 / kernel，但指定形状（1，20）和找到形状（4，20）
不幸的是，必须运行整个代码才能看到问题。这是jupyter笔记本的链接：https://github.com/verenalin/deepQ.git
任何帮助将不胜感激。
我检查了类之间的所有链接，但找不到解决方案。
class DeepQNetwork:
def __init__(
self,
n_actions,
n_features,
learning_rate=0.01,
reward_decay=0.9,
e_greedy=0.9,
replace_target_iter=10,
batch_size=5,
e_greedy_increment=None,
output_graph=None
):
self.n_actions = n_actions
self.n_features = n_features
self.lr = learning_rate
self.gamma = reward_decay
self.epsilon_max = e_greedy
self.replace_target_iter = replace_target_iter
self.memory_size = 100
self.batch_size = batch_size
self.epsilon_increment = e_greedy_increment
self.epsilon = 0 if e_greedy_increment is not None else self.epsilon_max
self.monthly_stock_history = []
# total learning step
self.learn_step_counter = 0
# initialize zero memory [s, a, r, s_]
self.memory = np.zeros((self.memory_size, n_features*2+2))
# consist of [target_net, evaluate_net]
self._build_net()
t_params = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='target_net')
e_params = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='eval_net')
with tf.variable_scope('soft_replacement'):
self.target_replace_op = [tf.assign(t, e) for t, e in zip(t_params, e_params)]
self.sess = tf.Session()
self.sess.run(tf.global_variables_initializer())
self.cost_his = []
def _build_net(self):
# ------------------ all inputs ------------------------
self.s = tf.placeholder(tf.float32, [None, self.n_features], name='s') # input State
self.s_ = tf.placeholder(tf.float32, [None, self.n_features], name='s_') # input Next State
self.r = tf.placeholder(tf.float32, [None, ], name='r') # input Reward
self.a = tf.placeholder(tf.int32, [None, ], name='a') # input Action
w_initializer, b_initializer = tf.random_normal_initializer(0., 0.3), tf.constant_initializer(0.1)
# ------------------ build evaluate_net ------------------
with tf.variable_scope('eval_net', reuse=tf.AUTO_REUSE):
e1 = tf.layers.dense(self.s, 20, tf.sigmoid, kernel_initializer=w_initializer,
bias_initializer=b_initializer, name='e1')
self.q_eval = tf.layers.dense(e1, self.n_actions, kernel_initializer=w_initializer,
bias_initializer=b_initializer, name='q')
# ------------------ build target_net ------------------
with tf.variable_scope('target_net', reuse=tf.AUTO_REUSE):
t1 = tf.layers.dense(self.s_, 20, tf.sigmoid, kernel_initializer=w_initializer,
bias_initializer=b_initializer, name='t1')
self.q_next = tf.layers.dense(t1, self.n_actions, kernel_initializer=w_initializer,
bias_initializer=b_initializer, name='t2')
with tf.variable_scope('q_target'):
q_target = self.r + self.gamma * tf.reduce_max(self.q_next, axis=1, name='Qmax_s_') # shape=(None, )
self.q_target = tf.stop_gradient(q_target)
with tf.variable_scope('q_eval'):
a_indices = tf.stack([tf.range(tf.shape(self.a)[0], dtype=tf.int32), self.a], axis=1)
self.q_eval_wrt_a = tf.gather_nd(params=self.q_eval, indices=a_indices) # shape=(None, )
with tf.variable_scope('loss'):
self.loss = tf.reduce_mean(tf.squared_difference(self.q_target, self.q_eval_wrt_a, name='TD_error'))
with tf.variable_scope('train', reuse=tf.AUTO_REUSE):
self._train_op = tf.train.RMSPropOptimizer(self.lr).minimize(self.loss)
尝试共享变量eval_net / e1 / kernel，但指定了形状(1, 20)并找到了形状(4, 20)