Premium Content

What Is Reinforcement Learning?

Framing learning from interaction

This chapter requires a subscription to access.

What you'll unlock:

  • 1. The Agent-Environment Loop
  • 2. The Reward Hypothesis
  • 3. RL vs Supervised vs Unsupervised
  • 4. A Short History: TD-Gammon to ChatGPT
  • 5. Two Cultures: Tabular Theory and Deep RL Practice
Subscribe to Unlock

Already have an account? Sign in