{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T16:29:10Z","timestamp":1648571350997},"reference-count":18,"publisher":"Walter de Gruyter GmbH","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,1,18]]},"abstract":"Abstract<\/jats:title>In order to proceed along an action sequence, an autonomous agent has to recognize that the intended final condition of the previous action has been achieved. In previous work, we have shown how a sequence of actions can be generated by an embodied agent using a neural-dynamic architecture for behavioral organization, in which each action has an intention and condition of satisfaction. These components are represented by dynamic neural fields, and are coupled to motors and sensors of the robotic agent.Here,we demonstratehowthemappings between intended actions and their resulting conditions may be learned, rather than pre-wired.We use reward-gated associative learning, in which, over many instances of externally validated goal achievement, the conditions that are expected to result with goal achievement are learned. After learning, the external reward is not needed to recognize that the expected outcome has been achieved. This method was implemented, using dynamic neural fields, and tested on a real-world E-Puck mobile robot and a simulated NAO humanoid robot.<\/jats:p>","DOI":"10.1515\/pjbr-2015-0011","type":"journal-article","created":{"date-parts":[[2015,11,19]],"date-time":"2015-11-19T08:56:42Z","timestamp":1447923402000},"source":"Crossref","is-referenced-by-count":2,"title":["Learning the Condition of Satisfaction of an Elementary Behavior in Dynamic Field Theory"],"prefix":"10.1515","volume":"6","author":[{"given":"Matthew","family":"Luciw","sequence":"first","affiliation":[]},{"given":"Sohrob","family":"Kazerounian","sequence":"additional","affiliation":[]},{"given":"Konstantin","family":"Lahkman","sequence":"additional","affiliation":[]},{"given":"Mathis","family":"Richter","sequence":"additional","affiliation":[]},{"given":"Yulia","family":"Sandamirskaya","sequence":"additional","affiliation":[]}],"member":"374","reference":[{"key":"ref81","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0893-6080(88)90021-4","article-title":"Nonlinear neural networks : Principles mechanisms and architectures","volume":"1","author":"Grossberg","year":"1988","journal-title":"Neural Networks"},{"key":"ref171","doi-asserted-by":"crossref","first-page":"1164","DOI":"10.1016\/j.neunet.2010.07.012","article-title":"and An embodied account of serial order : How instabilities drive sequence generation","volume":"23","author":"Yulia Sandamirskaya","year":"2010","journal-title":"Neural Networks"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-33269-2_4","article-title":"and A dynamic field architecture for the generation of hierarchically organized sequences In Alessandro E Francesco and editors Artificial Neural Networks and Machine Learning ICANN volume of Notes in pages","volume":"25","author":"Boris Duran","year":"2012","journal-title":"Lecture Computer Science"},{"key":"ref151","article-title":"A neuraldynamic architecture for behavioral organization of an embodied agent In Conference on Development and Learning and on Epigenetic Robotics ( ICDL","author":"Sandamirskaya","year":"2011","journal-title":"IEEE International"},{"key":"ref221","article-title":"Review dopamine signals for reward value and risk : basic and recent data Behav","volume":"6","author":"WolframSchultz","year":"2010","journal-title":"Brain Funct"},{"key":"ref211","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1177\/107385840100700406","article-title":"Reward signaling by dopamine neurons The","volume":"7","author":"Wolfram Schultz","year":"2001","journal-title":"Neuroscientist"},{"key":"ref281","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/BF00288786","article-title":"A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue","volume":"13","author":"Wilson","year":"1973","journal-title":"Kybernetik"},{"key":"ref271","first-page":"1","article-title":"Developmental robotics : Theory and experiments of","author":"Juyang Weng","year":"2004","journal-title":"International Journal Humanoid Robotics"},{"key":"ref101","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.newideapsych.2007.07.007","article-title":"Moving to higher ground : The dynamic field theory and the dynamics of visual cognition New in","volume":"26","author":"Johnson","year":"2008","journal-title":"Ideas Psychology"},{"key":"ref181","article-title":"Sebastian Schneegans and Using dynamic field theory to extend the embodiment stance toward higher cognition New in","author":"Yulia Sandamirskaya","year":"2013","journal-title":"Ideas Psychology"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1088\/1741-2560\/3\/3\/R02","article-title":"and The dynamic neural field approach to cognitive robotics of","volume":"3","author":"Wolfram Erlhagen","year":"2006","journal-title":"Journal Neural Engineering"},{"key":"ref31","first-page":"1","article-title":"and Motivational control of goal - directed action Animal Learning &","volume":"22","author":"Anthony Dickinson","year":"1994","journal-title":"Behavior"},{"key":"ref01","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/BF00337259","article-title":"Dynamics of pattern formation in lateral - inhibition type neural fields","volume":"27","author":"SAmari","year":"1977","journal-title":"Biological Cybernetics"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1037\/a0020887","article-title":"and Gianluca Baldassarre Tropicals : a computational embodied neuroscience model of compatibility effects","volume":"117","author":"Daniele Caligiore","year":"2010","journal-title":"Psychological Review"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1177\/02783640022066950","article-title":"Target representation on an autonomous vehicle with low - level sensors The of","volume":"19","author":"Bicho","year":"2000","journal-title":"International Journal Robotics Research"},{"key":"ref161","first-page":"276","article-title":"Dynamic neural fields as a step towards cognitive neuromorphic architectures Frontiers in","volume":"7","author":"Yulia Sandamirskaya","year":"2013","journal-title":"Neuroscience"},{"key":"ref241","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1111\/1467-7687.00295","article-title":"Bridging the representational gap in the dynamical systems approach to development","volume":"6","author":"Spencer","year":"2003","journal-title":"Developmental Science"},{"key":"ref131","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1037\/h0024475","article-title":"Two - process learning theory : Relationships between pavlovian conditioning and instrumental learning","volume":"74","author":"Rescorla","year":"1967","journal-title":"Psychological Review"}],"container-title":["Paladyn, Journal of Behavioral Robotics"],"original-title":[],"link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/pjbr-2015-0011\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T04:00:24Z","timestamp":1619064024000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/pjbr-2015-0011\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,18]]},"references-count":18,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1515\/pjbr-2015-0011","relation":{},"ISSN":["2081-4836"],"issn-type":[{"value":"2081-4836","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,18]]}}}