Machine Learning [KSR Wiki]

Diese Seite ist nicht editierbar. Du kannst den Quelltext sehen, jedoch nicht verändern. Kontaktiere den Administrator, wenn du glaubst, dass hier ein Fehler vorliegt.

# Machine Learning

## Syllabus
  * Git & GitHub: proficiency assumed
    * Otherwise: [[talit:git_github]]
  * Jupyter Notebook [1w] 
    * crash course: Edit, run, publish 
    * Login to shared notebook
    * setup your own server 
  * Q-Learning Intro [3w] 
    * Along the lines of [[https://github.com/microsoft/ML-For-Beginners/tree/main/8-Reinforcement|Microsoft ML Chapter 8]]
    * Assumes we can observe the entire state. 
    * Reward / action only depends on the current state of the game. 
    * Immediate reward given by game score (points) 
    * Q-Function is a table (Q-Table) dynamically updated by Bellman-formula 
  * Hidden Markov Models (a tiny bit of theory)
    * -> what if we cannot observe all the internal state? 
    * -> infer probability of hidden (latent) state from observations
  * Deep Reinforcement Learning 
    * Q-Function is not a table, but a neural network, which is trained by repeatedly running the game and updating the neuron states. 
    * builds on top of [[neuronales_netzwerk_handschrift:|sca's NN program]]
    * Prereqs:
      * OpenAI Gym environment: https://gym.openai.com/docs/
      * keras / tensorflow?