Skip to content
intai
Search lessonsCtrl K

Track 06

Coming soon

Reinforcement Learning & Self-Improving AI

Understand how models learn from feedback: reward design, preference optimisation, and the loops that make agents improve without drifting.

  • Advanced
  • Chapters coming soon
See what's planned

What this track will cover

The outcomes the published chapters will build toward.

  1. Explain how a reward signal shapes model behaviour
  2. Compare RLHF, preference optimisation, and simpler feedback loops
  3. Spot reward hacking and drift before they ship

Main subjects

The territory this track covers.

  1. 01Reward design
  2. 02Preference optimisation
  3. 03RLHF
  4. 04Feedback loops
  5. 05Agent improvement

Who this is for

Engineers and researchers moving beyond prompt-level improvements to learned behaviour.

Before you start

  • Basic probability and optimisation
  • Familiarity with supervised fine-tuning
  • Comfort reading research-style explanations

Curriculum

Chapters coming soon

In progress

Chapters are being written.

This track is scoped but not yet published. The subjects above are the planned path; lessons will appear here as each chapter is ready.

Browse learning tracks