Cornell RL Reading Group
xikronz.github.io · 131 words · saved by 1 readers
Cornell's reinforcement learning and interactive learning paper reading group.
Reinforcement learning is driving some of the most important capabilities in modern AI models right now: reasoning breakthroughs in frontier LLMs, the alignment of generative models, and the emergence of capable embodied agents. What does this mean for how we design learning algorithms? Which theoretical foundations explain the empirical successes of post-training at scale? In this reading group, we take a look at the algorithmic frontier of RL and how it reshapes the modern AI stack. Starting from entropy-based online methods and no-regret learning, we build up through sequential decision…
saved by
related reading
- www.1943aiml.com1943aiml.com
- Jubayer Ibn Hamidjubayer-ibn-hamid.github.io
- GRPO++: Tricks for Making RL Actually Workcameronrwolfe.substack.com
- RLHF | John Lambertjohnwlambert.github.io
- [2602.19362] LLMs Can Learn to Reason Via Off-Policy RLarxiv.org
- State of RL for reasoning LLMs | A. Weersaweers.de
- RLHF & Post-Training Course by Nathan Lambertrlhfbook.com
- The Extreme Inefficiency of RL for Frontier Models - Toby Ordtobyord.com
- GenAI Handbookgenai-handbook.github.io
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- RLHF: Reinforcement Learning from Human Feedbackhuyenchip.com
- The Iliad Intensive Course Materials — LessWronglesswrong.com