Loading...

Linear Fitted-Q Iteration with Multiple Reward Functions

We present a general and detailed development of an algorithm for finite-horizon fitted-Q iteration with an arbitrary number of reward signals and linear value function approximation using an arbitrary number of state features. This includes a detailed treatment of the 3-reward function case using t...

Fuld beskrivelse

Na minha lista:
Bibliografiske detaljer
Main Authors: Lizotte, Daniel J., Bowling, Michael, Murphy, Susan A.
Format: Artigo
Sprog:Inglês
Udgivet: 2012
Fag:
Online adgang:https://ncbi.nlm.nih.gov/pmc/articles/PMC3670261/
https://ncbi.nlm.nih.gov/pubmed/23741197
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!