{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T23:57:30Z","timestamp":1725667050270},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,8]]},"abstract":"<jats:p>Many stochastic search algorithms are designed to optimize a fixed objective function to learn a task, \n\ni.e., if the objective function changes slightly, for example, due to a change in the situation or context of the task, \n\nrelearning is required to adapt to the new context. For instance, if we want to learn a kicking movement for a soccer robot, \n\nwe have to relearn the movement for different ball locations. Such relearning is undesired as it is highly inefficient \n\nand many applications require a fast adaptation to a new context\/situation. Therefore, we investigate contextual stochastic search \n\nalgorithms that can learn multiple, similar tasks simultaneously. Current contextual stochastic search methods are based \n\non policy search algorithms and suffer from premature convergence and the need for parameter tuning. \n\nIn this paper, we extend the well known CMA-ES algorithm to the contextual setting and illustrate its performance on several contextual tasks. \n\nOur new algorithm, called contextual CMA-ES, leverages from contextual learning while it preserves all the features of standard CMA-ES such \n\nas stability, avoidance of premature convergence, step size control and a minimal amount of parameter tuning.<\/jats:p>","DOI":"10.24963\/ijcai.2017\/191","type":"proceedings-article","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T09:14:07Z","timestamp":1501233247000},"page":"1378-1385","source":"Crossref","is-referenced-by-count":4,"title":["Contextual Covariance Matrix Adaptation Evolutionary Strategies"],"prefix":"10.24963","author":[{"given":"Abbas","family":"Abdolmaleki","sequence":"first","affiliation":[{"name":"University of Aveiro"},{"name":"University of Porto"},{"name":"University of Minho"}]},{"given":"Bob","family":"Price","sequence":"additional","affiliation":[{"name":"Palo Alto Research Centre (PARC), A Xerox Company"}]},{"given":"Nuno","family":"Lau","sequence":"additional","affiliation":[{"name":"University of Aveiro"}]},{"given":"Luis","family":"Paulo Reis","sequence":"additional","affiliation":[{"name":"University of Minho"},{"name":"University of Porto"}]},{"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[{"name":"University of Lincoln"},{"name":"University of Darmstadt"}]}],"member":"10584","event":{"number":"26","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)","University of Technology Sydney (UTS)","Australian Computer Society (ACS)"],"acronym":"IJCAI-2017","name":"Twenty-Sixth International Joint Conference on Artificial Intelligence","start":{"date-parts":[[2017,8,19]]},"theme":"Artificial Intelligence","location":"Melbourne, Australia","end":{"date-parts":[[2017,8,26]]}},"container-title":["Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T11:52:41Z","timestamp":1501242761000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2017\/191"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2017,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2017\/191","relation":{},"subject":[],"published":{"date-parts":[[2017,8]]}}}