Lecture 9, Reinforcement Learning [Örjan]
Tid: Måndag 7 oktober 2013 kl 17:00 - 19:00
Plats: D1
Aktivitet: Föreläsning
Studentgrupper: TCSCM1-AS, TCSCM1-BER, TCSCM1-PRS, TCSCM1-SPR, TITMM2, TIVNM1, TKOMK3, TMAIM1, TMAIM1-BIO, TMAIM1-IR, TMAIM1-PC, TSCRM1, TSCRM2
Info:
Reinforcement Learning
Readings: Marsland: chapter 13
- Is it possible to learn when nobody tells you the correct answer?
- Central terms: State, Action, Reward
- More terms: Value function (cumulative value), Policy
- How can we judge the consequences of our actions?
- What do we mean by an optimal behavior?
- Is it possible to learn what is the best thing to do in each state?
- Is it possible to learn faster by planning ahead?