Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

- Experiment error traceback (use --gdb to debug) - #4

Open
zhq99 opened this issue Jan 6, 2018 · 0 comments
Open

- Experiment error traceback (use --gdb to debug) - #4

zhq99 opened this issue Jan 6, 2018 · 0 comments

Comments

@zhq99
Copy link

zhq99 commented Jan 6, 2018

Hi~
when I debug, there was something wrong. I was wondering if you could kindly help me?

The information is

  • Experiment error traceback (use --gdb to debug) -
    experiment.py : 175 : execute : self.main()
    run.py : 199 : main : Experiment().run()
    run.py : 72 : run : env_dtype=str(self.env.action_space.high.dtype))
    ddpg.py : 70 : init : act_test, sum_p = nets.policy(obs, self.theta_p) if not FLAGS.batch_norm else nets.policy_norm(obs, self.theta_p, is_training)
    ddpg_nets_dm.py : 50 : policy : summary = hist_summaries(h0,h1,h2,h3,action)
    ddpg_nets_dm.py : 8 : hist_summaries : return tf.summary.merge_all([tf.summary.histogram(t.name,t) for t in args])
    TypeError: unhashable type: 'list'
    Exception gym.error.Error: Error('env has been garbage collected. To keep using a monitor, you must keep around a reference to the env object. (HINT: try assigning the env to a variable in your code.)',) in <bound method Monitor.del of <gym.monitoring.monitor.Monitor object at 0x7fae02531210>> ignored
    Elapsed seconds: 1238.30144286

Thanks~

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant