{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T01:44:50Z","timestamp":1649036690677},"reference-count":6,"publisher":"World Scientific Pub Co Pte Lt","issue":"05","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Artif. Intell. Tools"],"published-print":{"date-parts":[[2006,10]]},"abstract":"<jats:p> Reinforcement learning (RL) has been successfully used in many fields. With the increasing complexity of environments and tasks, it is difficult for a single learning algorithm to cope with complicated problems with high performance. This paper proposes a new multiple learning architecture, \"Aggregated Multiple Reinforcement Learning System (AMRLS)\", which aggregates different RL algorithms in each learning step to make more appropriate sequential decisions than those made by individual learning algorithms. This architecture was tested on a Cart-Pole system. The presented simulation results confirm our prediction and reveal that aggregation not only provides robustness and fault tolerance ability, but also produces more smooth learning curves and needs fewer learning steps than individual learning algorithms. <\/jats:p>","DOI":"10.1142\/s0218213006002990","type":"journal-article","created":{"date-parts":[[2006,10,17]],"date-time":"2006-10-17T12:26:00Z","timestamp":1161087960000},"page":"855-861","source":"Crossref","is-referenced-by-count":4,"title":["AGGREGATION OF MULTIPLE REINFORCEMENT LEARNING ALGORITHMS"],"prefix":"10.1142","volume":"15","author":[{"given":"JU","family":"JIANG","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"MOHAMED S.","family":"KAMEL","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"LEI","family":"CHEN","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2011,11,21]]},"reference":[{"key":"rf1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"rf2","series-title":"A Bradford Book","volume-title":"Reinforcement Learning, An Introduction","author":"Sutton Richard S.","year":"1998"},{"key":"rf3","first-page":"279","volume":"8","author":"Watkins C. J. C. H.","journal-title":"Machine Learning"},{"key":"rf4","first-page":"79","author":"Jacobs R.","journal-title":"Neural Computation"},{"key":"rf5","first-page":"1409","author":"Jordan M.","journal-title":"Neural Networks"},{"key":"rf8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"}],"container-title":["International Journal on Artificial Intelligence Tools"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218213006002990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T22:32:29Z","timestamp":1565130749000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218213006002990"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,10]]},"references-count":6,"journal-issue":{"issue":"05","published-online":{"date-parts":[[2011,11,21]]},"published-print":{"date-parts":[[2006,10]]}},"alternative-id":["10.1142\/S0218213006002990"],"URL":"https:\/\/doi.org\/10.1142\/s0218213006002990","relation":{},"ISSN":["0218-2130","1793-6349"],"issn-type":[{"value":"0218-2130","type":"print"},{"value":"1793-6349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,10]]}}}