You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Dear authors:
Thanks for designing tf_agents! I've encountered a problem when I was running the code of google research project called circuit-training. It created an object of Learner (we can call it learner). When it came to learner.run, it called learner._train. I added some log for help. In the outcome, I found that all log was printed out in learner._train, indicating _train was done. However, in learner.run, the log instructions right after calling learner._train was never printed out, which means that the function was actually not returned (the whole training process got stuck). How could this happen? I got no idea. Could you give me some advice? Thanks a lot!!!!
defrun(self, iterations=1, iterator=None, parallel_iterations=10):
""" ... """# do things...withself.train_summary_writer.as_default(), \
common.soft_device_placement(), \
tf.compat.v2.summary.record_if(_summary_record_if), \
self.strategy.scope():
iterator=iteratororself._experience_iteratorloss_info=self._train(tf.constant(iterations),
iterator,
parallel_iterations)
logging.info("return back to run") # never printed outtrain_step_val=self.train_step.numpy()
fortriggerinself.triggers:
trigger(train_step_val)
returnloss_info@common.function(autograph=True)def_train(self, iterations, iterator, parallel_iterations):
# ...logging.info("_train start") # printed out# do thingslogging.info("_train end") # printed outreturnreduced_loss_info
@misc{CircuitTraining2021,
title = {{Circuit Training}: An open-source framework for generating chip
floor plans with distributed deep reinforcement learning.},
author = {Guadarrama, Sergio and Yue, Summer and Boyd, Toby and Jiang, Joe
Wenjie and Songhori, Ebrahim and Tam, Terence and Mirhoseini, Azalia},
howpublished = {\url{https://github.com/google_research/circuit_training}},
url = "https://github.com/google_research/circuit_training",
year = 2021,
note = "[Online; accessed 21-December-2021]"
}
The text was updated successfully, but these errors were encountered:
Dear authors:
Thanks for designing tf_agents! I've encountered a problem when I was running the code of google research project called circuit-training. It created an object of
Learner
(we can call itlearner
). When it came tolearner.run
, it calledlearner._train
. I added some log for help. In the outcome, I found that all log was printed out inlearner._train
, indicating_train
was done. However, inlearner.run
, the log instructions right after callinglearner._train
was never printed out, which means that the function was actually not returned (the whole training process got stuck). How could this happen? I got no idea. Could you give me some advice? Thanks a lot!!!!The text was updated successfully, but these errors were encountered: