Dive into RL

Overview

This session covers reinforcement learning fundamentals and practical training insights relevant to post-training and reasoning-oriented LLM pipelines.

Papers

1. ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
2. Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
3. JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Slides

• Download PDF