Learning

Teaching the robot instead of programming it: data with labels, nearest neighbour, a tiny neural network, learning by reward, models as text.

Module 8Robot club8 lessons

Start in the simulator
  1. 8.1 See as numbers What a model gets: the sensor views as lists of numbers.
  2. 8.2 Collecting data Readings with labels, and why bad data makes bad robots.
  3. 8.3 Nearest neighbour The simplest classifier, in a dozen lines.
  4. 8.4 A tiny network Weights, a loss, and watching it fall: training in the browser.
  5. 8.5 Learning by reward Q-learning: a table of how good each action is, filled in by trying.
  6. 8.6 Tuning itself Learning a controller gain by trial: measure, change, keep the better.
  7. 8.7 Models as text Saving and loading a model with JSON; models trained elsewhere.
  8. 8.8 Project: situations A classifier decides what the robot does next.