haku: @author Bolton, P. / yhteensä: 19
viite: 15 / 19
Tekijä: | Aghion, P. Bolton, P. Harris, C. |
Otsikko: | Optimal learning by experimentation |
Lehti: | Review of Economic Studies
1991 : JUL, VOL. 58:196, p.621-654 |
Asiasana: | LEARNING OPTIMIZATION DECISION MAKING ACTION LEARNING |
Kieli: | eng |
Tiivistelmä: | A problem of optimal learning by experimentation by a single decision maker is considered. Most of the analysis is concerned with the characterisation of limit beliefs and actions. A two-stage approach is taken to this problem: first the case where the agent's payoff function is deterministic is understood, then the additional issues arising when noise is present are addressed. The analysis indicates that local properties of the payoff function are crucial in determining whether the agent eventually attains the true maximum payoff or not. A limited attempt is made at characterising optimal experimentation strategies. |
SCIMA