[英]Tensorflow Reinforcement Learning RNN returning NaN's after Optimization with GradientTape
def create_example_model():
tf.keras.backend.set_floatx('float64')
model = Sequential()
model.add(LSTM(128, input_shape=((60, len(df_train.columns)))))
model.add(Dense(64, activation='relu'))
model.add(Dense(3, activation=None))
return model
def choose_action(model, observation):
observation = np.expand_dims(observation, axis=0)
logits = model.predict(observation)
prob_weights = tf.nn.softmax(logits).numpy()
action = np.random.choice(3, size=1, p=prob_weights.flatten())[0]
return action
def train_step(model, optimizer, observations, actions, discounted_rewards):
with tf.GradientTape() as tape:
logits = model(observations)
loss = compute_loss(logits, actions, discounted_rewards)
grads = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(grads, model.trainable_variables))
learning_rate = 1e-3
optimizer = tf.keras.optimizers.Adam(learning_rate)
env = TradingEnv(rnn_ready_array)
model = create_example_model()
memory = Memory()
info_list = []
for i_episode in range(10):
observation = env.reset()
memory.clear()
while True:
action = choose_action(model, observation)
next_observation, reward, done, info = env.step(action)
info_list.append(info)
memory.add_to_memory(observation, action, reward)
if done:
total_reward = sum(memory.rewards)
train_step(model, optimizer,
observations=np.array(memory.observations),
actions=np.array(memory.actions),
discounted_rewards = discount_rewards(memory.rewards))
memory.clear()
break
observation = next_observation
I am working on a reinforcement learning project with Tensorflow 2.0;我正在使用 Tensorflow 2.0 进行强化学习项目; the format of the code comes from an online MIT course of which I am attempting to adapt to my own project.
代码格式来自麻省理工学院的一个在线课程,我正在尝试适应我自己的项目。 I am new to Tensorflow 2.0 and I can't glean from the documentation why this problem is occurring.
我是 Tensorflow 2.0 的新手,我无法从文档中了解为什么会出现此问题。 The issue is that when I run the reinforcement learning process,
问题是当我运行强化学习过程时,
Some debugging info I have found that should be helpful: If I comment out the optimization lines 'grads = tape.gradient(...)' and 'optimizer.apply_gradients(...)' the script will run to completion error free (though it is obviously not doing anything useful without optimization).我发现一些调试信息应该会有所帮助:如果我注释掉优化行 'grads = tape.gradient(...)' 和 'optimizer.apply_gradients(...)' 脚本将运行完成无错误(尽管没有优化它显然没有做任何有用的事情)。 This indicates to me the optimization process is changing the model in a way that is causing the problem.
这向我表明优化过程正在以导致问题的方式更改 model。 I've tried to include only the necessary functions for debugging;
我试图只包含调试所需的功能; if there is any further information one might need for debugging, I'd be happy to add additional info in an edit.
如果调试时可能需要任何进一步的信息,我很乐意在编辑中添加其他信息。
After hours of checking and rechecking various containers I realized it was the discounted rewards function that was not working properly, returning NaN in this circumstance.经过数小时检查和重新检查各种容器后,我意识到打折奖励 function 无法正常工作,在这种情况下返回 NaN。 Issue resolved:)
问题解决了:)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.