Syllabus helps researchers study CL in complex, open-ended environments without having to write new multiprocessing infrastructure. It uses a separate multiprocessing channel between the curriculum and environments to directly send new tasks and receive feedback - ThreadSky

ryanpsullivan.bsky.social • 174 days ago

Syllabus helps researchers study CL in complex, open-ended environments without having to write new multiprocessing infrastructure. It uses a separate multiprocessing channel between the curriculum and environments to directly send new tasks and receive feedback

Comments

ryanpsullivan.bsky.social•174 days ago

Most importantly, it’s extremely easy to use! You add a synchronization wrapper to your environments and your curriculum, plus a little more configuration, and it just works. For most methods, you don’t need to make any changes to the actual training logic.

ryanpsullivan.bsky.social•174 days ago

These portable implementations of CL methods work with nearly any RL library, meaning that you only need to implement the method once to guarantee that the same CL code is being used in every project. This minimizes the risk of implementation errors and promotes reproducibility.

ryanpsullivan.bsky.social•174 days ago

We have implementations of Prioritized Level Replay, a learning progress curriculum, and Prioritized Fictitious Self Play, plus several tools for manually designing curricula like simulated annealing and sequential curricula. Stay tuned for more methods in the very near future!

ryanpsullivan.bsky.social•174 days ago

I’d like to thank my collaborators @ryan-pgd.bsky.social, Ameen Ur Rehman, Xinchen Yang, Junyun Huang, Aayush Verma, Nistha Mitra, and John P. Dickerson as well as @minqi.bsky.social, @samvelyan.com, and Jenny Zhang for their valuable feedback and answers to my many implementation questions.

ryanpsullivan.bsky.social•174 days ago

Syllabus opens up a ton of low hanging fruit in CL. I’m still working on this and actively using it for my research, so if you’re interested in contributing, please feel free to reach out!

Paper: https://arxiv.org/abs/2411.11318
Github: https://github.com/RyanNavillus/Syllabus

ryanpsullivan.bsky.social•174 days ago

I have a lot more experiments from working on Syllabus so I’ll share more of those over the next few weeks. Now is probably a good time to mention I’m also looking for industry or postdoc positions starting in Fall 2024, so if you’re working on anything RL-related let me know!

Comments

Posting Rules

Reply