> ## Documentation Index
> Fetch the complete documentation index at: https://aegean.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Markov Decision Processes

> Introduction to MDPs, Bellman equations, policy evaluation, and value iteration.

<CardGroup cols={2}>
  <Card title="Introduction to MDPs (Part 1)" icon="play" href="https://www.youtube.com/watch?v=15d1-FZJKP4">
    Defining Markov Decision Processes
  </Card>

  <Card title="Introduction to MDPs (Part 2)" icon="play" href="https://www.youtube.com/watch?v=_EZ78z5ryo0">
    Defining Markov Decision Processes
  </Card>

  <Card title="Bellman Expectation (Part 1)" icon="play" href="https://www.youtube.com/watch?v=e2fz3nNjNcQ">
    Deriving the Bellman Expectation Equations
  </Card>

  <Card title="Bellman Expectation (Part 2)" icon="play" href="https://www.youtube.com/watch?v=M8Gadmn8pA8">
    Deriving the Bellman Expectation Equations
  </Card>

  <Card title="Policy Evaluation (Part 1)" icon="play" href="https://www.youtube.com/watch?v=GU-QPMKBNUE">
    Using Bellman for Policy Evaluation
  </Card>

  <Card title="Policy Evaluation (Part 2)" icon="play" href="https://www.youtube.com/watch?v=PELHvCblayI">
    Using Bellman for Policy Evaluation
  </Card>

  <Card title="Bellman Optimal Value Functions" icon="play" href="https://www.youtube.com/watch?v=C4sloVtHSwo">
    Deriving the Bellman Optimality Equations
  </Card>

  <Card title="Policy and Value Iteration" icon="play" href="https://www.youtube.com/watch?v=SSYDYSmGi1E">
    Using Bellman for optimal control
  </Card>
</CardGroup>

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit this page on GitHub](https://github.com/aegean-ai/eaia/edit/main/src/media/planning/markov-decision-processes.mdx) or [file an issue](https://github.com/aegean-ai/eaia/issues/new/choose).
</Callout>