xikronz/rl-reading-group

This repository is the website and materials home for a reinforcement learning and interactive learning reading group run by CUAI, a student AI group at Cornell. It is not a piece of software you install or run. Instead, it is a place to find the group's schedule, reading list, and related resources, and to suggest papers you would like the group to cover by opening an issue on GitHub. The README lays out a rough summer syllabus covering six broad topics: online learning algorithms and games, sequential decision making and Markov decision processes, policy gradient methods, reinforcement learning for large language models, reinforcement learning for AI agents, and reinforcement learning for consistency models. The exact week-by-week schedule was still being finalized at the time this README was written. The group also mentions a lineup of guest speakers coming from Cornell, MIT, and Stanford, as well as from companies including Mercor and Citadel Securities. For anyone who wants to study these topics more deeply on their own, the README links out to a handful of external courses and references: two Cornell reinforcement learning courses at the graduate and undergraduate level, an interactive learning algorithms course from Carnegie Mellon, a Stanford course on building language models from scratch, an online reinforcement learning theory textbook, and a separate GitHub list of notable reinforcement learning papers. Beyond the syllabus, the reading list, and these external links, the README does not describe any code, tools, or installable software in this repository. It reads as a lightweight companion page for an in-person or virtual reading group rather than a software project. The README does not mention a license.