Sign in

Ryan Sullivan

@ryanpsullivan.bsky.social
59 followers 56 following 22 posts

Postdoc at UBC with Jeff Clune. PhD from UMD. Researching reinforcement learning and autocurricula in complex, open-ended environments. Previously RL intern @ SonyAI, RLHF intern @ Google Research, and RL intern @ Amazon Science

PostsRepliesMedia
Ryan Sullivan @ryanpsullivan.bsky.social · 05/12/2024
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.
121
Ryan Sullivan @ryanpsullivan.bsky.social · 05/12/2024
As a result, CL research often focuses on relatively simple environments, despite the existence of challenging benchmarks like NetHack, Minecraft, and Neural MMO. Unsurprisingly, many of the methods developed in simpler environments won’t work as well on more complex domains.
111