Processing math: 100%

Wiki

A universe of ideas

User Tools

Site Tools


uni:8:ml:start

This is an old revision of the document!


Maschinelles Lernen und Data Mining

Reinforcement Learning

Agent → Actions → Environment
← state ←
← reward ←
  1. Learner is not told what to do
  2. Trial and error search
  3. Delayed reward
  4. We need to explore round exploit
  • Policy what to do
  • Reward what is good
  • Value what is good because it predicts reward
  • Model what follows what

Evaluating feedback

  • Evaluating actions vs. inst???
  • Example: n-armed bandit
    • evaluate feedback
  • after each play at we got a reward r_t where E{rtat}=Q(at)
  • optimize reward ??? 1000 plays
  • Exploration/
    • ??? Qt(a)=Q(a) action value estimate
    • ???
  • at=at ⇒ exploitation
  • atat ⇒ exploration
Action Value Methods

Suppose by the ??? play actions a had been choosen ka times, producing rewards r1,r2,rk,a Qt(a)=r1,r2,rk,aka limkQt(a)=Q(a)

\epsilon-feeding action selection
  • feeding: at=at=avgamaxQt(a)
  • ϵ-feeding = at????
In the 10-Armed test bed
  • n=10 possible actions
  • Each Q^*(a) is chosen rounding from N(0,1)
  • 1000 plays, avergage our 2000 experiments
Softmax action selection
  • Softmax grade action probabilities by estimated values Qt
  • Bolzmann-distribution: π(at)=eQt(a)/τnb=1eQt(b)/τ
uni/8/ml/start.1434011243.txt.gz · Last modified: 2020-11-18 18:10 (external edit)