Linear Fitted-Q Iteration with Multiple Reward Functions.
about
Dynamic Treatment RegimesMulti-Objective Markov Decision Processes for Data-Driven Decision SupportEstimation of optimal dynamic treatment regimesInteractive model building for Q-learning.Adaptive Interventions in Child and Adolescent Mental HealthSet-valued dynamic treatment regimes for competing outcomes.Incorporating Patient Preferences into Estimation of Optimal Individualized Treatment Rules.
P2860
Q30597725-A1E24C97-C407-4530-AC33-08BE0CDB14A3Q31151283-EF5A533F-F178-48AB-AD14-509A53C74617Q34585577-A1384A9A-C28A-4BCA-9665-AEED68333ACBQ34760298-00740873-061A-478C-829F-55CB39130F15Q37059108-6A96FA8F-29A6-4DEF-8BE4-108857B15F73Q37637697-988B2DA0-AFCC-4012-B0E5-FF00D094FDC6Q38662474-8471F7CB-631C-48B7-BA8C-9A48B987236B
P2860
Linear Fitted-Q Iteration with Multiple Reward Functions.
description
2012 nî lūn-bûn
@nan
2012年の論文
@ja
2012年論文
@yue
2012年論文
@zh-hant
2012年論文
@zh-hk
2012年論文
@zh-mo
2012年論文
@zh-tw
2012年论文
@wuu
2012年论文
@zh
2012年论文
@zh-cn
name
Linear Fitted-Q Iteration with Multiple Reward Functions.
@en
type
label
Linear Fitted-Q Iteration with Multiple Reward Functions.
@en
prefLabel
Linear Fitted-Q Iteration with Multiple Reward Functions.
@en
P2860
P1476
Linear Fitted-Q Iteration with Multiple Reward Functions.
@en
P2093
Daniel J Lizotte
P2860
P304
P407
P577
2012-11-01T00:00:00Z