Radix
×

Reinforcement Learning

23 people already started

About this learning path

Reinforcement Learning

Machine learning paradigm concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward.

It comes from

  • ↑ Machine Learning
  • includes the learning paths

  • - Dynamic Programming
  • and can be deepened into

  • ↓ Deep Reinforcement Learning
  • Web resources
    Start immediately and learn at your own pace.

    Flexible schedule
    Set and adhere to flexible deadlines.

    Approx. 4 months to complete
    Recommended 12 hours/week

    Mostly English

    Curator

    There is no curator for
    Reinforcement Learning yet!

    This How it Works

    You go station by station. In each station you'll find resources containing:

    1. Information

    2. Educational content

    3. Places to exchange infos

    4. Applications, Tools

    ( 5. Entertaining content )

    After studying a resource, you check it.

    Between stations, sometimes there are learning paths. They need to be studied as well as they pose a qualification for upcoming content. After station 1, the learning path for Dynamic Programming needs to be studied.

    After finishing this learning path, you can specialize further or apply what you learned in another learning path.

    Learning Path

    Station

    1

    Station

    2

    »

    Hidden Markov Models Model

    »

    Markov Decision Process

     

    Gym Library

    »

    Reinforcement Learning Lectures

    »

    Reinforcement learning

    »

    Reinforcement Learning: An Introduction Non-fictional

    Station

    3

     

    Markov Chain Monte Carlo Method

    »

    Reinforcement Learning State-of-the-Art Non-fictional

    »

    Algorithms for Reinforcement Learning

    Station

    4

     

    Q-learning