keras：attributeError：＆＃x27; adam＆＃x27;对象没有属性＆＃x27; name＆＃x27;

Question

我想编译我的DQN代理，但我会发现错误： attributeError：'adam'对象没有属性'_name'，

DQN = buildAgent(model, actions)
DQN.compile(Adam(lr=1e-3), metrics=['mae'])

我尝试添加伪造_name ，但它不起作用，我正在关注教程，并且可以在Tutor上使用它机器，这可能是一些新的更新更改，但是如何

在这里解决此问题是我的完整代码：

from keras.layers import Dense, Flatten
import gym
from keras.optimizer_v1 import Adam
from rl.agents.dqn import DQNAgent
from rl.policy import BoltzmannQPolicy
from rl.memory import SequentialMemory

env = gym.make('CartPole-v0')
states = env.observation_space.shape[0]
actions = env.action_space.n

episodes = 10

def buildModel(statez, actiones):
    model = Sequential()
    model.add(Flatten(input_shape=(1, statez)))
    model.add(Dense(24, activation='relu'))
    model.add(Dense(24, activation='relu'))
    model.add(Dense(actiones, activation='linear'))
    return model

model = buildModel(states, actions)

def buildAgent(modell, actionz):
    policy = BoltzmannQPolicy()
    memory = SequentialMemory(limit=50000, window_length=1)
    dqn = DQNAgent(model=modell, memory=memory, policy=policy, nb_actions=actionz, nb_steps_warmup=10, target_model_update=1e-2)
    return dqn

DQN = buildAgent(model, actions)
DQN.compile(Adam(lr=1e-3), metrics=['mae'])
DQN.fit(env, nb_steps=50000, visualize=False, verbose=1)

Answer 1

我的2美分：使用旧式凯拉斯优化器！

#from tensorflow.keras.optimizers import Adam
from tensorflow.keras.optimizers.legacy import Adam

就我而言，它有效。

Answer 2

您的错误来自adam与来自keras.optimizer_v1导入adam，您可以使用tf.keras.optimizers.adam.adam从<<<<<代码> tensorflow＆gt; = v2 喜欢下面：

（lr参数已弃用，最好使用Learning_rate而不是。）

# !pip install keras-rl2
import tensorflow as tf
from keras.layers import Dense, Flatten
import gym
from rl.agents.dqn import DQNAgent
from rl.policy import BoltzmannQPolicy
from rl.memory import SequentialMemory

env = gym.make('CartPole-v0')
states = env.observation_space.shape[0]
actions = env.action_space.n
episodes = 10

def buildModel(statez, actiones):
    model = tf.keras.Sequential()
    model.add(Flatten(input_shape=(1, statez)))
    model.add(Dense(24, activation='relu'))
    model.add(Dense(24, activation='relu'))
    model.add(Dense(actiones, activation='linear'))
    return model

def buildAgent(modell, actionz):
    policy = BoltzmannQPolicy()
    memory = SequentialMemory(limit=50000, window_length=1)
    dqn = DQNAgent(model=modell, memory=memory, policy=policy, 
                   nb_actions=actionz, nb_steps_warmup=10, 
                   target_model_update=1e-2)
    return dqn

model = buildModel(states, actions)
DQN = buildAgent(model, actions)
DQN.compile(tf.keras.optimizers.Adam(learning_rate=1e-3), metrics=['mae'])
DQN.fit(env, nb_steps=50000, visualize=False, verbose=1)

Answer 3

#pip install keras == 2.11.0

#pip install tensorflow == 2.11.0

dqn.compile（tf.keras.optimizers.legacy.adam（learning_rate = 1e-3），量表= ['mae'']）