Completed
- The added value in RL
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Reinforcement Learning and Fine-Tuning on TPUs - The Agent Factory Podcast
Automatically move to the next video in the Classroom when playback concludes
- 1 - Introduction: Gemini 3 and the rise of TPUs
- 2 - Why fine-tune? Specialization and privacy
- 3 - What is fine-tuning? SFT and RL explained
- 4 - What is RL and why do we need it?
- 5 - The added value in RL
- 6 - Industry pulse: Why 2025 is the year of RL DeepSeek-R1, Grok 4, Gemini 3
- 7 - The challenges of RL: Infrastructure, algorithms, and orchestration
- 8 - Factory floor: How TPUs are designed for scale
- 9 - [Demo] Reinforcement Learning GRPO with MaxText 2.0 on TPUs
- 10 - Scaling to 1000+ chips and season wrap up
