Computing near-optimal policies from trajectories by solving a sequence of standard supervised learning problems

Speech/Talk (Diverse speeches and writings)

Ernst, Damien

2006

Permalink
https://hdl.handle.net/2268/173581

ernst-fittedQiteration.pdf

Publisher postprint (335.04 kB)

All documents in ORBi are protected by a user license.

Keywords :

Reinforcement learning; Supervised learning; Optimal control theory

Disciplines :

Computer science

Author, co-author :

Ernst, Damien ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids

Language :

English

Title :

Computing near-optimal policies from trajectories by solving a sequence of standard supervised learning problems

Publication date :

November 2006

Event place :

Control Group, TU Delft, Netherlands

Audience :

International

Commentary :

[Talk given at several other places]

Available on ORBi :

since 04 November 2014

Number of views

30 (3 by ULiège)

Number of downloads

158 (3 by ULiège)