Q Learning

• The premise: learn the optimal action a for state s directly

• The function Q(s, a) is (an estimate of) the expected future reward associated with executing a in state s:

• • from Q(s,a) the optimal action ?*(s) is obtained by taking the max
  • we want to learn this Q function directly

• Learning framework: repeatedly

  • Takes some action dictated by the Q function
  • Gets some reward r
  • Updates Q function appropriately

Previous slide

Next slide

Back to first slide

View graphic version