Please use this identifier to cite or link to this item:

TitleContextual covariance matrix adaptation evolutionary strategies
Author(s)Abdolmaleki, Abbas
Price, Bob
Lau, Nuno
Reis, L. P.
Neumann, Gerhard
Issue date2017
PublisherInternational Joint Conferences on Artificial Intelligence Organization (IJCAI)
JournalIJCAI International Joint Conference on Artificial Intelligence
Abstract(s)Many stochastic search algorithms are designed to optimize a fixed objective function to learn a task, i.e., if the objective function changes slightly, for example, due to a change in the situation or context of the task, relearning is required to adapt to the new context. For instance, if we want to learn a kicking movement for a soccer robot, we have to relearn the movement for different ball locations. Such relearning is undesired as it is highly inefficient and many applications require a fast adaptation to a new context/situation. Therefore, we investigate contextual stochastic search algorithms that can learn multiple, similar tasks simultaneously. Current contextual stochastic search methods are based on policy search algorithms and suffer from premature convergence and the need for parameter tuning. In this paper, we extend the well known CMA-ES algorithm to the contextual setting and illustrate its performance on several contextual tasks. Our new algorithm, called contextual CMAES, leverages from contextual learning while it preserves all the features of standard CMA-ES such as stability, avoidance of premature convergence, step size control and a minimal amount of parameter tuning.
TypeConference paper
Publisher version
AccessOpen access
Appears in Collections:DSI - Engenharia da Programação e dos Sistemas Informáticos

Files in This Item:
File Description SizeFormat 
2017_IJCAI_Contextual Covariance Matrix Adaptation Evolutionary Strategies.pdf832,11 kBAdobe PDFView/Open

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID