NVlabs / GA3C

Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.
BSD 3-Clause "New" or "Revised" License
652 stars 195 forks source link

Playing hangs after last episode #21

Open ErnstTmp opened 7 years ago

ErnstTmp commented 7 years ago

Hi, I am running testing(playing) for 500 iterations. And then I want to automatically start and other job. But I can not do that, because the 2 of the 3 GA3C jobs do not end and need to be killed by .

The reasons seems to be that the predictor gets stuck and waits for an agent that is already terminated (see the end of Server.py / ThreadPredictor.py). Could you please look at that?

Thanks, Ernst

mbz commented 7 years ago

Related to #4

ErnstTmp commented 7 years ago

Thanks, do you have any ideas how I could fix this?