Hey There SlimyRat21
We did a small integration of Trains with a Doom agent that uses reinforcement learning.
https://github.com/erezalg/ViZDoom
What we did is basically change a bit the strcuture of how parameters are cought (so we can modify them from the UI), then logged stuff like loss, location on the map, frame buffers at certain times and information about end of episode that might be helpful for us.
You can see how it looks on the demoapp (as long as it lasts 🙂 )
Let me know if you want to consult further!
https://demoapp.trains.allegro.ai/projects/066fc0bddf6147ba8ad9dbf3069e1b1d/experiments/ac85011177d24b09895509d42a8abd7d/execution?columns=selected&columns=type&columns=name&columns=tags&columns=status&columns=project.name&columns=user.name&columns=started&columns=last_update&columns=last_iteration&order=last_update
Hi SlimyRat21 :
Tool that will help me track and manage the different configs and simulation logs across different runs and versions of the simulation.
Definitely covered by Trains, it also does that with very little code changes (if any) to your current code base
Tool that will help me gather and compare the results from specific simulation runs
Same as above 🙂
Do you you have an experience or tips on using trains for non-ML before investing time into this and seeing for myself? Or do you know of another tool you could recommend? Thank you!
I think we used it for our RL Doom agent, is this a similar case ?
Thanks for the reply! I am not familiar with the Rl Doom agent, but I will look for it!