Premium Content

Markov Decision Processes

The formal language of RL

This chapter requires a subscription to access.

What you'll unlock:

  • 1. States, Actions, Transitions, Rewards
  • 2. Returns, Discounting, and Episodes
  • 3. Policies and Value Functions
  • 4. Bellman Expectation Equations
  • 5. Bellman Optimality Equations
  • 6. POMDPs and the Contraction-Mapping Proof
Subscribe to Unlock

Already have an account? Sign in