Signin

DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs

Julia Turc • March 23, 2025
Video Thumbnail

You May Also Like

Video Thumbnail

Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains

Perimeter Institute for Theoretical Physics

Video Thumbnail

Mixture of Experts Explained: From Vowel Recognition to Trillion-Parameter LLMs (Llama 4, DeepSeek)

Julia Turc

Video Thumbnail

[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Yannic Kilcher

Video Thumbnail

Training LLM to play chess using Deepseek GRPO reinforcement learning

Efficient NLP

Video Thumbnail

Reinforcement Learning for Agents - Will Brown, ML Researcher at Morgan Stanley

AI Engineer

Video Thumbnail

Apache Iceberg™ | What It Is and Why Everyone’s Talking About It

Confluent Developer

Video Thumbnail

RAG vs. CAG: Solving Knowledge Gaps in AI Models

IBM Technology

Video Thumbnail

How DeepSeek Rewrote the Transformer [MLA]

Welch Labs

Video Thumbnail

How Linux is built with Greg Kroah-Hartman

The Pragmatic Engineer

Video Thumbnail

The Real Reason Windows is Free - And what that costs you!

Dave's Garage

Video Thumbnail

Yann LeCun "Mathematical Obstacles on the Way to Human-Level AI"

Joint Mathematics Meetings

Video Thumbnail

THIS Is Why Gen Z Are The Poorest Generation

The Infographics Show

Video Thumbnail

How does GRPO work?

Trelis Research

Video Thumbnail

Proximal Policy Optimization (PPO) for LLMs Explained Intuitively

Julia Turc

Video Thumbnail

I Trained an LLM to Think Deeper (Here's How)

Adam Lucek

Video Thumbnail

How might LLMs store facts | DL7

3Blue1Brown

Video Thumbnail

Proximal Policy Optimization (PPO) - How to train Large Language Models

Serrano.Academy

Video Thumbnail

Why LLMs get dumb (Context Windows Explained)

NetworkChuck

Video Thumbnail

Proximal Policy Optimization Explained

Edan Meyer

Video Thumbnail

The Man Who Almost Broke Math (And Himself...)

Veritasium

Julia Turc

View Channel

About

No channel description available.

Latest Posts

Video Thumbnail

Knowledge Distillation: How LLMs train each other

Julia Turc

Video Thumbnail

DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs

Julia Turc

Video Thumbnail

Mixture of Experts Explained: From Vowel Recognition to Trillion-Parameter LLMs (Llama 4, DeepSeek)

Julia Turc

Video Thumbnail

Proximal Policy Optimization (PPO) for LLMs Explained Intuitively

Julia Turc

AI Assistant

Loading...