|Reference : Variable selection for dynamic treatment regimes: a reinforcement learning approach|
|Scientific congresses and symposiums : Unpublished conference/Abstract|
|Engineering, computing & technology : Multidisciplinary, general & others|
Engineering, computing & technology : Computer science
|Variable selection for dynamic treatment regimes: a reinforcement learning approach|
|Fonteneau, Raphaël [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]|
|Wehenkel, Louis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]|
|Ernst, Damien [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]|
|European Workshop on Reinforcement Learning 2008 (EWRL'08)|
|30 June - 3 July|
|[en] dynamic treatment regimes ; reinforcement learning ; fitted Q iteration|
|[en] Dynamic treatment regimes (DTRs) can be inferred from data collected through some randomized clinical trials by using reinforcement learning algorithms. During these clinical trials, a large set of clinical indicators are usually monitored. However, it is often more convenient for clinicians to have DTRs which are only defined on a small set of indicators rather than on the original full set. To address this problem, we analyse the approximation architecture of the state-action value functions computed by the fitted Q iteration algorithm - a RL algorithm - using tree-based regressors in order to identify a small subset of relevant ones. The RL algorithm is then rerun by considering only as state variables these most relevant indicators to have DTRs defined on a small set of indicators. The approach is validated on benchmark problems inspired
from the classical ‘car on the hill’ problem and the results obtained are positive.
|Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS|
|File(s) associated to this reference|
All documents in ORBi are protected by a user license.