以下代码适用于TensorFlow中的Deep Q Network。
运行此程序时，初始化TensorFlow变量时发生OOM错误。我认为这是因为我的实验模型有更大的动作集(例如3125000个动作(。我制作了自己的模拟器，它以元组(大约50到100个数字(的形式返回状态，所以我不需要使用卷积层。
错误消息如下：
tensorflow/stream_executor/cuda/cuda_driver.cc:967] failed to alloc 17179869184 bytes on host: CUDA_ERROR_OUT_OF_MEMORY
./tensorflow/core/common_runtime/gpu/pool_allocator.h:195] could not allocate pinned host memory of size: 1179869184
我该如何处理这个问题？请帮帮我…
系统环境是Ubuntu 16.04与TITAN X(Pascal(
class DQN:
def __init__(self, n_features, n_action, lr, dr, max_e_greedy, e_increment, replace_target_iter, memory_size, batch_size):
self.n_features = n_features
self.n_actions = n_action
self.lr = lr
self.gamma = dr
self.max_e = max_e_greedy
self.replace_target_iter = replace_target_iter
self.memory_size = memory_size
self.batch_size = batch_size
self.e = 0
self.e_increment = e_increment
self.learn_step = 0
self.memory = np.zeros((self.memory_size, n_features*2 + 2))
self.cost_his=[]
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())
def build_net(self):
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)
with tf.variable_scope('eval_net'):
e1 = tf.layers.dense(self.s, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='e1')
e2 = tf.layers.dense(e1, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='e2')
#e3 = tf.layers.dense(e2, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='e3')
#e4 = tf.layers.dense(e3, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='e4')
self.q_eval=tf.layers.dense(e2, self.n_actions, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='q')
with tf.variable_scope('target_net'):
t1 = tf.layers.dense(self.s_, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='t1')
t2 = tf.layers.dense(t1, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='t2')
#t3 = tf.layers.dense(t2, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='t3')
#t4 = tf.layers.dense(t3, 800, tf.nn.relu, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='t4')
self.q_next=tf.layers.dense(t2, self.n_actions, kernel_initializer=w_initializer, bias_initializer=b_initializer, name='t5')
with tf.variable_scope('q_target'):
q_target = self.r + self.gamma * tf.reduce_max(self.q_next, axis=1, name='Qmax_s_')
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'):
self._train_op = tf.train.RMSPropOptimizer(self.lr).minimize(self.loss)
谢谢！！
Tensorflow尝试将GPU内存的一部分per_process_gpu_memory_fraction分配给进程。(请参阅Tensorflow源的GPU选项中的注释(。默认设置为95%。如果该值更改为GPU无法处理的值，则可能会出现CUDA_OUT_OF_MEMORY错误。如果另一个进程正在使用GPU并占用Tensorflow认为会有的内存，也可能会引发此错误。
如果你想避免使用CPU，你可以使用allow_growth=True。当您使用allow_growth = True时，GPU内存没有预先分配，可以根据需要增长。