Python ValueError:试图转换';张量';一个张量,失败了。错误:参数必须是稠密张量:
当我切断线路时Python ValueError:试图转换';张量';一个张量,失败了。错误:参数必须是稠密张量:,python,tensorflow,neural-network,reinforcement-learning,Python,Tensorflow,Neural Network,Reinforcement Learning,当我切断线路时 tf.reshape(rewards_list, [-1, 25]) 我听到一个错误说 ValueError: Cannot feed value of shape (1, 1, 25) for Tensor 'Placeholder_3:0', which has shape '(?, 25)' 但是当我把它放在那里时,我在标题中得到了错误信息 ValueError: Tried to convert 'tensor' to a tensor and failed. Err
tf.reshape(rewards_list, [-1, 25])
我听到一个错误说
ValueError: Cannot feed value of shape (1, 1, 25) for Tensor 'Placeholder_3:0', which has shape '(?, 25)'
但是当我把它放在那里时,我在标题中得到了错误信息
ValueError: Tried to convert 'tensor' to a tensor and failed. Error: Argument must be a dense tensor: [array([[0.4758947]], dtype=float32)] - got shape [1, 1, 1], but wanted [1].
我不明白发生了什么事。奖励列表怎么可能是这两种形状
observations = tf.placeholder('float32', shape=[None, num_stops]) # Current game states : r[stop], r[next_stop], r[third_stop]
actions = tf.placeholder('int32',shape=[None]) # 0 - num-stops for actions taken
rewards = tf.placeholder('float32',shape=[None]) # +1, -1 with discounts
# Model
Y = tf.layers.dense(observations, 200, activation=tf.nn.relu)
Ylogits = tf.layers.dense(Y, num_stops)
# sample an action from predicted probabilities
sample_op = tf.random.categorical(logits=Ylogits, num_samples=1)
# loss
cross_entropies = tf.losses.softmax_cross_entropy(onehot_labels=tf.one_hot(actions,num_stops), logits=Ylogits)
loss = tf.reduce_sum(rewards * cross_entropies)
# training operation
optimizer = tf.train.RMSPropOptimizer(learning_rate=0.001, decay=.99)
train_op = optimizer.minimize(loss)
visited_stops = []
steps = 0
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# Start at a random stop, initialize done to false
current_stop = random.randint(0, len(r) - 1)
done = False
# reset everything
while not done: # play a game in x steps
observations_list = []
actions_list = []
rewards_list = []
# List all stops and their scores
observation = r[current_stop]
# Add the stop to a list of non-visited stops if it isn't
# already there
if current_stop not in visited_stops:
visited_stops.append(current_stop)
# decide where to go
action = sess.run(sample_op, feed_dict={observations: [observation]})
# play it, output next state, reward if we got a point, and whether the game is over
#game_state, reward, done, info = pong_sim.step(action)
new_stop = int(action)
reward = r[current_stop][action]
if len(visited_stops) == num_stops:
done = True
if steps >= BATCH_SIZE:
done = True
steps += 1
observations_list.append(observation)
actions_list.append(action)
rewards_list.append(reward)
#rewards_list = np.reshape(rewards, [-1, 25])
current_stop = new_stop
#processed_rewards = discount_rewards(rewards, args.gamma)
#processed_rewards = normalize_rewards(rewards, args.gamma)
tf.reshape(rewards_list, [-1, 25])
sess.run(train_op, feed_dict={observations: [observations_list],
actions: [actions_list],
rewards: rewards_list})
请张贴整个图表,而不仅仅是它的执行让我知道,如果有什么我可以做的。谢谢您的
奖励值是多少?大小为25的向量?什么是np.数组(奖励列表).shape
打印?奖励值访问大小为[25,25]的矩阵。这是一个25站的距离矩阵。奖励是距离的1/2。