SkyRL Meetup

From reasoning models and coding assistants to autonomous agents, Reinforcement Learning (RL) is changing how foundation models are trained, adapted, and deployed. SkyRL is a modular open-source library for agentic RL, developed at UC Berkeley Sky Lab in collaboration with Anyscale. SkyRL has quickly grown to be one of the most popular RL libraries over the past year, with 2k+ GitHub stars and a growing user base in academia and industry, including researchers from Stanford, CMU, UC Berkeley, Microsoft AI, Datadog, and more.Join us for the first-ever SkyRL meetup! Meet fellow AI engineers, researchers, and builders for an evening of lightning talks and networking, covering how people are building with SkyRL, a deep dive into the library, and the road ahead.AGENDA6:00 PM – Doors open, food, and networking 6:15 PM – Lightning talks from SkyRL users Chuck Tang, Research Engineer, Trajectory - "Open Weights Aren't Enough: Frontier RL Training for Everyone"Eddie Richter & Pratik Mishra, MTS, AMD - “Scaling Reinforcement Learning with SkyRL on AMD”Ben Cohen, Staff Research Scientist, Datadog - “Post-training an SRE Agent with SkyRL”Charlie Ruan, UC Berkeley/Mercor - “Training Knowledge Work Agents with SkyRL” 7:00 PM – SkyRL technical deep-dive Eric Tang, Software Engineer, AnyscaleSumanth Hegde, Software Engineer, Anyscale 7:15 PM – Open networkingHosted by: Anyscale, the company behind the Ray open source project, is a fully managed AI platform for foundation model-scale workloads. AI teams use it to run data, training, inference, and RL workloads at scale on any cloud.