Brenden Petersen

Thanks for the quick response! And again, I understand on the serious lack of details in the paper! My background is more on the RL side, but I'm new to...

I've just switched from PPO1 to PPO2 after they cleaned up their codebase and added MPI support for PPO2. Unfortunately, performance on my environments using PPO2 (with the same hyperparameters...

I found a timely publication: https://arxiv.org/pdf/1811.02553.pdf. This paper raises many questions about TRPO/PPO, both w.r.t. each algorithm and its implementation. In one set of experiments, it actually references the baselines-implementation-specific...

Thank you for your interest! You are correct: the "hall of fame" is a record of the top `hof` programs ever seen during training, as measured by `r`. It sounds...

Sorry for the delayed reply! `n_cores_batch` only works if you are otherwise running DSO in a single process. If you are perhaps running DSO in parallel some other way, it...

@edfink234 What OS are you using? @snapo Thank you very much for providing a Dockerfile. I think we could take that as a PR if you'd like to create one....

This is a great idea, thanks! We should add this to the README. Our updated version for the symbolic regression task called uDSR, just published in NeurIPS 2022 (code update...

We updated our repo and now include those results in our README :)

@tluchko Good point, unfortunately we weren't able to include the AIF or LSPT components in this release. Though if you look at the ablations in our paper, it hardly makes...

Sorry I missed this earlier. This is an interesting question. I don't see a simple solution, but it's definitely doable by implementing custom versions of DSO core abstractions. I think...