openai/coinrun

trouble with fetching the logs

Unimax opened this issue · 2 comments

Unimax commented

I am trying to recreate the figure 6 in the paper which show the effect of all the known techniques on performance for coinrun. Need help with the following if possible.

  • starting new training just clear the directory and delete all previous logs!!

  • the train with --test seems not to produce enough information on tensorboard. rew_mean_<run_id> is the mean reward for testing on random levels I suppose. training mean reward results are missing?

image

  • resuming the training starts the episodes and total timestamps from 0 shouldn't it start from the previous numbers. (i can see the model is loaded and getting improved). its ends up with wrong graphs in the tensorboard.

  • what changes come into mind if I try to apply DQN here?

Thanks in advance

sanjayyyyyy commented

How do we fetch the logs after testing

Unimax commented

default dir is '/tmp/tensorflow'
use tensorboard to plot the logs
note: by default, it will remove all previous logs. idk why they wanted that.