Christian Hidber

Actually we were contemplating about an extension to EasyAgents where you could easily provide an "arbitrary" nn, eg defined in keras or so. However it wasn't obvious to us how...

:-)

Hi Oliver Yes you are right, when you load a previously saved model and start training it will start from scrach. We had a similar issue a few weeks ago...

splendid, that sounds exciting. all the best.

Great idea. Indeed it shouldn't be too difficult to integrate. Are you already using rllib ?

I just looked into ray/rllib. It seems that windows is still not supported: https://github.com/ray-project/ray/issues/2683 . At least pip install failed on Windows 10. That's a target platform of easyagents. :-(

Splendid, thanks for the hint. I'll definitely take a look at it.