@inproceedings{
 title = {Ventilation control learning with FACL},
 type = {inproceedings},
 keywords = {Analytical models,Atmosphere,FACL,Fuzzy control,Fuzzy logic,Fuzzy systems,Industrial control,Iron,Learning systems,Optimal control,Ventilation,building atmosphere control,fuzzy actor-critic learning,fuzzy control,fuzzy reinforcement functions,learning (artificial intelligence),optimal control,optimal policies,reinforcement learning method,ventilation,ventilation control learning},
 pages = {1719-1724},
 volume = {3},
 websites = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=619799},
 publisher = {IEEE},
 id = {2d656178-d15a-36df-895b-b14c87ea94f2},
 created = {2015-04-23T15:15:45.000Z},
 accessed = {2015-04-23},
 file_attached = {false},
 profile_id = {95e10851-cdf3-31de-9f82-1ab629e601b0},
 group_id = {f4f27d7f-2273-33eb-bbb9-78e3e17cc268},
 last_modified = {2017-03-14T09:42:43.424Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 language = {English},
 private_publication = {false},
 abstract = {Fuzzy actor-critic learning (FACL) is a reinforcement learning method that tunes fuzzy controllers (FC). Based only on reinforcement signals, such as rewards and punishments, that describe the control task, FACL qualifies FC's actions to approximate optimal policies. One of the most important user step is to define good reinforcement functions. In this article, we introduce fuzzy reinforcement functions (FRF) to describe the task in such a way that the frontiers between success and failure states become smooth. This new type of reinforcement function brings more informations than the classical one, allowing a higher learning speed. We apply these FRFs with FACL on an industrial task that consists in controlling a building atmosphere.},
 bibtype = {inproceedings},
 author = {Jouffe, L.},
 doi = {10.1109/FUZZY.1997.619799},
 booktitle = {Proceedings of 6th International Fuzzy Systems Conference}
}

{"_id":"mJDmdwxyciCMCFGQq","authorIDs":["HArEHmShDY84JsJfE"],"author_short":["Jouffe, L."],"bibbaseid":"jouffe-ventilationcontrollearningwithfacl","bibdata":{"title":"Ventilation control learning with FACL","type":"inproceedings","keywords":"Analytical models,Atmosphere,FACL,Fuzzy control,Fuzzy logic,Fuzzy systems,Industrial control,Iron,Learning systems,Optimal control,Ventilation,building atmosphere control,fuzzy actor-critic learning,fuzzy control,fuzzy reinforcement functions,learning (artificial intelligence),optimal control,optimal policies,reinforcement learning method,ventilation,ventilation control learning","pages":"1719-1724","volume":"3","websites":"http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=619799","publisher":"IEEE","id":"2d656178-d15a-36df-895b-b14c87ea94f2","created":"2015-04-23T15:15:45.000Z","accessed":"2015-04-23","file_attached":false,"profile_id":"95e10851-cdf3-31de-9f82-1ab629e601b0","group_id":"f4f27d7f-2273-33eb-bbb9-78e3e17cc268","last_modified":"2017-03-14T09:42:43.424Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"language":"English","private_publication":false,"abstract":"Fuzzy actor-critic learning (FACL) is a reinforcement learning method that tunes fuzzy controllers (FC). Based only on reinforcement signals, such as rewards and punishments, that describe the control task, FACL qualifies FC's actions to approximate optimal policies. One of the most important user step is to define good reinforcement functions. In this article, we introduce fuzzy reinforcement functions (FRF) to describe the task in such a way that the frontiers between success and failure states become smooth. This new type of reinforcement function brings more informations than the classical one, allowing a higher learning speed. We apply these FRFs with FACL on an industrial task that consists in controlling a building atmosphere.","bibtype":"inproceedings","author":"Jouffe, L.","doi":"10.1109/FUZZY.1997.619799","booktitle":"Proceedings of 6th International Fuzzy Systems Conference","bibtex":"@inproceedings{\n title = {Ventilation control learning with FACL},\n type = {inproceedings},\n keywords = {Analytical models,Atmosphere,FACL,Fuzzy control,Fuzzy logic,Fuzzy systems,Industrial control,Iron,Learning systems,Optimal control,Ventilation,building atmosphere control,fuzzy actor-critic learning,fuzzy control,fuzzy reinforcement functions,learning (artificial intelligence),optimal control,optimal policies,reinforcement learning method,ventilation,ventilation control learning},\n pages = {1719-1724},\n volume = {3},\n websites = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=619799},\n publisher = {IEEE},\n id = {2d656178-d15a-36df-895b-b14c87ea94f2},\n created = {2015-04-23T15:15:45.000Z},\n accessed = {2015-04-23},\n file_attached = {false},\n profile_id = {95e10851-cdf3-31de-9f82-1ab629e601b0},\n group_id = {f4f27d7f-2273-33eb-bbb9-78e3e17cc268},\n last_modified = {2017-03-14T09:42:43.424Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n language = {English},\n private_publication = {false},\n abstract = {Fuzzy actor-critic learning (FACL) is a reinforcement learning method that tunes fuzzy controllers (FC). Based only on reinforcement signals, such as rewards and punishments, that describe the control task, FACL qualifies FC's actions to approximate optimal policies. One of the most important user step is to define good reinforcement functions. In this article, we introduce fuzzy reinforcement functions (FRF) to describe the task in such a way that the frontiers between success and failure states become smooth. This new type of reinforcement function brings more informations than the classical one, allowing a higher learning speed. We apply these FRFs with FACL on an industrial task that consists in controlling a building atmosphere.},\n bibtype = {inproceedings},\n author = {Jouffe, L.},\n doi = {10.1109/FUZZY.1997.619799},\n booktitle = {Proceedings of 6th International Fuzzy Systems Conference}\n}","author_short":["Jouffe, L."],"urls":{"Website":"http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=619799"},"biburl":"https://bibbase.org/service/mendeley/95e10851-cdf3-31de-9f82-1ab629e601b0","bibbaseid":"jouffe-ventilationcontrollearningwithfacl","role":"author","keyword":["Analytical models","Atmosphere","FACL","Fuzzy control","Fuzzy logic","Fuzzy systems","Industrial control","Iron","Learning systems","Optimal control","Ventilation","building atmosphere control","fuzzy actor-critic learning","fuzzy control","fuzzy reinforcement functions","learning (artificial intelligence)","optimal control","optimal policies","reinforcement learning method","ventilation","ventilation control learning"],"metadata":{"authorlinks":{"jouffe, l":"https://www.bayesia.com/"}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/95e10851-cdf3-31de-9f82-1ab629e601b0","creationDate":"2015-04-23T16:15:07.494Z","downloads":0,"keywords":["analytical models","atmosphere","facl","fuzzy control","fuzzy logic","fuzzy systems","industrial control","iron","learning systems","optimal control","ventilation","building atmosphere control","fuzzy actor-critic learning","fuzzy control","fuzzy reinforcement functions","learning (artificial intelligence)","optimal control","optimal policies","reinforcement learning method","ventilation","ventilation control learning"],"search_terms":["ventilation","control","learning","facl","jouffe"],"title":"Ventilation control learning with FACL","year":null,"dataSources":["8hwkQbNZz66Dc7LzM","ya2CyA73rpZseyrZ8"]}