Contextual stochastic search

Abdolmaleki, A. and Lau, N. and Paulo Reis, L. and Neumann, G. (2016) Contextual stochastic search. In: Genetic and Evolutionary Computation Conference GECCO 2016, 20 - 24 Juky 2016, Denver, Colorado.

Documents
25679 p29-abdolmaleki.pdf

Request a copy
[img] PDF
25679 p29-abdolmaleki.pdf - Whole Document
Restricted to Repository staff only

917kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Stochastic search algorithms have recently also gained a lot of attention in operations research, machine learning and policy search of robot motor skills due to their ease of use and their generality. Yet, many stochastic search algorithms require relearning if the task changes slightly to adapt the solution to the new situation or the new context. Therefore we consider the contextual stochastic search setup. Here, we want to find good parameter vectors for multiple related tasks, where each task is described by a continuous context vector. Hence, the objective might change slightly for each parameter vector evaluation. In this research, we investigate the contextual stochastic search algorithms that can learn from multiple tasks simultaneously.

Keywords:Search algorithms
Subjects:G Mathematical and Computer Sciences > G440 Human-computer Interaction
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25679
Deposited On:19 May 2017 11:43

Repository Staff Only: item control page