Reinforcement Learning (RL) for LLMs

Natasha Jaques March 12, 2025
Video Thumbnail
Natasha Jaques Logo

Natasha Jaques

View Channel

About

I'm an assistant professor at the University of Washington and a Staff Research Scientist at Google DeepMind. I give talks about my research on AI, machine learning, and reinforcement learning. If you want to learn more, check out my website https://natashajaques.ai/.

Video Description

Lecture on reinforcement learning (RL) fine-tuning of large language models (LLMs). Even though we are in the RL era for training LLMs, this didn't start with DeepSeek R1, or even ChatGPT. The talk takes a deep dive through the history of RL training of LLMs, including my own early work on RL from human feedback (RLHF). Then we discuss more recent techniques to achieve personalized RLHF, and the future of RL for LLMs, including using multi-agent RL for adversarial red-teaming.

You May Also Like