flâneur

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