Nalaganje...

Uncertainty and Exploration

In order to discover the most rewarding actions, agents must collect information about their environment, potentially foregoing reward. The optimal solution to this “explore-exploit” dilemma is often computationally challenging, but principled algorithmic approximations exist. These approximations u...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
izdano v:Decision (Wash D C )
Glavni avtor: Gershman, Samuel J.
Format: Artigo
Jezik:Inglês
Izdano: 2018
Teme:
Online dostop:https://ncbi.nlm.nih.gov/pmc/articles/PMC7989061/
https://ncbi.nlm.nih.gov/pubmed/33768122
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1037/dec0000101
Oznake: Označite
Brez oznak, prvi označite!