@INPROCEEDINGS{opponent-smc02,
  author = {Agapito Ledezma and Ricardo Aler and Araceli Sanchis and Daniel Borrajo},
  title = {Predicting Opponent actions in the RoboSoccer},
  booktitle = {Proceedings of the 2002 IEEE International Conference on Systems,
	Man and Cybernetics},
  year = {2002},
  volume = {7},
  address = {Hammamet, Tunisia},
  month = {October},
  abstract = {A very important issue in multi-agent systems is that of adaptability
	to other agents, be it to cooperate or to compete. In competitive
	domains, the knowledge about the opponent can give any player a clear
	advantage. In previous work, we acquired models of another agent
	(the opponent) based only on the observation of its inputs and outputs
	(its behavior) by formulating the problem as a classification task.
	In this paper we extend this previous work to the RoboCup domain.
	However, we have found that models based on a single classifier have
	bad accuracy, To solve this problem, In this paper we propose to
	decompose the learning task into two tasks: learning the action name
	(i.e. kick or dash) and learning the parameter of that action. By
	using this hierarchical learning approach accuracy results improve,
	and at worst, the agent can know what action the opponent will carry
	out, even if there is no high accuracy on the action parameter.},
  bib2html_pubtype = {Refereed Conference},
  bib2html_rescat = {Agent Modeling},
  days = {6--9},
  isbn = {0-7803-7437-1},
  key = {modelado},
  owner = {ledezma},
  timestamp = {2011.11.21}
}

{"_id":{"_str":"5342634f0e946d920a000d9c"},"__v":15,"authorIDs":["5457199e2abc8e9f3700006b","54575aa32abc8e9f370002ec","54576e722abc8e9f370003c4","5469957ebc7d6a460d00140f","8mdzoMZ27yguKiBHc"],"author_short":["Ledezma, A.","Aler, R.","Sanchis, A.","Borrajo, D."],"bibbaseid":"ledezma-aler-sanchis-borrajo-predictingopponentactionsintherobosoccer-2002","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Agapito"],"propositions":[],"lastnames":["Ledezma"],"suffixes":[]},{"firstnames":["Ricardo"],"propositions":[],"lastnames":["Aler"],"suffixes":[]},{"firstnames":["Araceli"],"propositions":[],"lastnames":["Sanchis"],"suffixes":[]},{"firstnames":["Daniel"],"propositions":[],"lastnames":["Borrajo"],"suffixes":[]}],"title":"Predicting Opponent actions in the RoboSoccer","booktitle":"Proceedings of the 2002 IEEE International Conference on Systems, Man and Cybernetics","year":"2002","volume":"7","address":"Hammamet, Tunisia","month":"October","abstract":"A very important issue in multi-agent systems is that of adaptability to other agents, be it to cooperate or to compete. In competitive domains, the knowledge about the opponent can give any player a clear advantage. In previous work, we acquired models of another agent (the opponent) based only on the observation of its inputs and outputs (its behavior) by formulating the problem as a classification task. In this paper we extend this previous work to the RoboCup domain. However, we have found that models based on a single classifier have bad accuracy, To solve this problem, In this paper we propose to decompose the learning task into two tasks: learning the action name (i.e. kick or dash) and learning the parameter of that action. By using this hierarchical learning approach accuracy results improve, and at worst, the agent can know what action the opponent will carry out, even if there is no high accuracy on the action parameter.","bib2html_pubtype":"Refereed Conference","bib2html_rescat":"Agent Modeling","days":"6–9","isbn":"0-7803-7437-1","key":"opponent-smc02","owner":"ledezma","timestamp":"2011.11.21","bibtex":"@INPROCEEDINGS{opponent-smc02,\r\n author = {Agapito Ledezma and Ricardo Aler and Araceli Sanchis and Daniel Borrajo},\r\n title = {Predicting Opponent actions in the RoboSoccer},\r\n booktitle = {Proceedings of the 2002 IEEE International Conference on Systems,\r\n\tMan and Cybernetics},\r\n year = {2002},\r\n volume = {7},\r\n address = {Hammamet, Tunisia},\r\n month = {October},\r\n abstract = {A very important issue in multi-agent systems is that of adaptability\r\n\tto other agents, be it to cooperate or to compete. In competitive\r\n\tdomains, the knowledge about the opponent can give any player a clear\r\n\tadvantage. In previous work, we acquired models of another agent\r\n\t(the opponent) based only on the observation of its inputs and outputs\r\n\t(its behavior) by formulating the problem as a classification task.\r\n\tIn this paper we extend this previous work to the RoboCup domain.\r\n\tHowever, we have found that models based on a single classifier have\r\n\tbad accuracy, To solve this problem, In this paper we propose to\r\n\tdecompose the learning task into two tasks: learning the action name\r\n\t(i.e. kick or dash) and learning the parameter of that action. By\r\n\tusing this hierarchical learning approach accuracy results improve,\r\n\tand at worst, the agent can know what action the opponent will carry\r\n\tout, even if there is no high accuracy on the action parameter.},\r\n bib2html_pubtype = {Refereed Conference},\r\n bib2html_rescat = {Agent Modeling},\r\n days = {6--9},\r\n isbn = {0-7803-7437-1},\r\n key = {modelado},\r\n owner = {ledezma},\r\n timestamp = {2011.11.21}\r\n}\r\n\r\n","author_short":["Ledezma, A.","Aler, R.","Sanchis, A.","Borrajo, D."],"id":"opponent-smc02","bibbaseid":"ledezma-aler-sanchis-borrajo-predictingopponentactionsintherobosoccer-2002","role":"author","urls":{},"downloads":0,"html":"","metadata":{"authorlinks":{"ledezma, a":"http://www.caos.inf.uc3m.es/ledezma/ca/publicaciones/"}}},"bibtype":"inproceedings","biburl":"http://www.caos.inf.uc3m.es/bibs/pubCAOS.bib","downloads":0,"keywords":[],"search_terms":["predicting","opponent","actions","robosoccer","ledezma","aler","sanchis","borrajo"],"title":"Predicting Opponent actions in the RoboSoccer","year":2002,"dataSources":["Z4T4fewybNpYCWveD"]}