Ray Summit 2022
In this 30-min talk, we will go over some of RLlib 2.0's biggest improvements, including:
Our goal for all this work is to make RLlib intuitive, easy to extend, and performant for various research and production use cases.
Jun Gong is a senior member of the ML team at Anyscale working on RLlib. He is a co-author of a Nature publication on the topic of stratospheric balloon navigation using reinforcement learning. Before Anyscale, he had extensive experience working on distributed and ML systems at Google and Facebook.
Sven Mika has been working as a machine learning engineer for Anyscale since early 2020. He is the lead developer of RLlib, Ray's industry-grade, scalable reinforcement learning (RL) library. His team is currently focusing on better supporting the most promising industry use cases, such as massive-multi-agent algorithms for league-based self-play, working with recommender systems and slate recommendation algos such as contextual bandits, and integrating with Ray's new datasets library for a better offline RL experience. A continuing effort of his is asserting high levels of stability and test coverage to ensure RLlib's rapid adoption in industry and research and helping to grow its community and contributor base. Before starting at Anyscale, he has been a leading developer of other successful open-source RL library projects, such as RLgraph and TensorForce.
Come connect with the global community of thinkers and disruptors who are building and deploying the next generation of AI and ML applications.Save your spot