maciej-sypetkowski / autoascend Goto Github PK

If I want to do behavior cloning on this agent, is it possible to do something like Dagger where I collect the data using an RL agent but query the teacher (AutoAscend) to get what action it would have taken instead?

Hi,

When running the following command python3 ./bin/main.py simulate -n 100 --panic-on-errors --no-plot, the code seems to hang on some of the last simulations (e.g. it finishes around 98 of them but then hangs). From what I can tell, it seems to hang on this line https://github.com/maciej-sypetkowski/autoascend/blob/master/bin/main.py#L309. Is this a known issue? Happy to dig a bit deeper but wanted to check here first.

Thank you!

I'd really appreciate it if you could mention the hardware you used to compete. This would give me an idea if an independent researcher can hope to do something in this area or is it mostly like LLMs, exclusively for large companies with huge amount of compute.