Matlab reinforcement learning stop working after a while

Hello,

I am not sure about the reason, but the toolbox stop working after reaching a number of episodes. Especially, this happens when I havea large number of episodes. The PC that I am using is very powerfull, so I am not sure what is the reason: Here is an screenshot of the freezing episode for number of hours.

Answer 1

[Emmanouil Tzorakoleftherakis]

125 episodes are not that many. Is it always freezing on that episode? Given that you are not getting any errors/crashes, my hunch is that there is something going on on the simulation side that creates this delay; either the system is stiff or something similar. Maybe try to replicate what's happening in these episodes to make sure. Also, try to reduce the number of logged signals in case this is a memory issue.

If these suggestions don't help, I would try contacting technical support.