{"id":"https://openalex.org/W2131574156","doi":"https://doi.org/10.1109/csie.2009.587","title":"Research and Application of Reinforcement Learning Based on Constraint MDP in Coal Mine","display_name":"Research and Application of Reinforcement Learning Based on Constraint MDP in Coal Mine","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2131574156","doi":"https://doi.org/10.1109/csie.2009.587","mag":"2131574156"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/csie.2009.587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074810229","display_name":"Zhao Xiao-hu","orcid":"https://orcid.org/0000-0002-4804-2168"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Xiao-hu","raw_affiliation_strings":["Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062676073","display_name":"Zhao Ke-ke","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Ke-ke","raw_affiliation_strings":["Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638422","display_name":"Qingqing Wang","orcid":"https://orcid.org/0000-0001-5613-3054"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Qing-qing","raw_affiliation_strings":["Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051646085","display_name":"Ma Fang-qing","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma Fang-qing","raw_affiliation_strings":["Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China"],"affiliations":[{"raw_affiliation_string":"Coll. of Inf. & Electr., China Univ. of Min. & Technol., Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":1,"citation_normalized_percentile":{"value":0.25337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":64,"max":71},"biblio":{"volume":null,"issue":null,"first_page":"687","last_page":"691"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T13832","display_name":"Advanced Decision-Making Techniques","score":0.9427,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13832","display_name":"Advanced Decision-Making Techniques","score":0.9427,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8975599},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.71906877},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.65991986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.64320123},{"id":"https://openalex.org/C108615695","wikidata":"https://www.wikidata.org/wiki/Q12880211","display_name":"Coal mining","level":3,"score":0.6112725},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5585252},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49821448},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.49418786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47908884},{"id":"https://openalex.org/C518851703","wikidata":"https://www.wikidata.org/wiki/Q24489","display_name":"Coal","level":2,"score":0.4542258},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44040838},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36428583},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36356544},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23547149},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1364128},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/csie.2009.587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":2,"referenced_works":["https://openalex.org/W2911283634","https://openalex.org/W2914656440"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3168977894","https://openalex.org/W3096874164","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2341346307","https://openalex.org/W2315999538","https://openalex.org/W2145363145","https://openalex.org/W1985560493","https://openalex.org/W1626977535"],"abstract_inverted_index":{"Reinforcement":[0,25],"learning":[1,9,26],"is":[2,8,67],"an":[3,28],"algorithm":[4,109,119],"without":[5],"model":[6],"which":[7,34],"what":[10],"to":[11,13,16,19,31,38,126],"do--how":[12],"map":[14],"situations":[15],"actions-so":[17],"as":[18],"maximize":[20],"a":[21,52,116],"numerical":[22],"reward":[23,54],"signal.":[24],"provides":[27],"available":[29],"method":[30],"the":[32,62,78,85,95,127,136,139,143,159,162],"systems,":[33],"are":[35],"very":[36],"difficult":[37],"build":[39],"up":[40],"accurate":[41],"models":[42],"around":[43],"complex":[44],"environment.":[45],"But":[46],"now":[47],"many":[48],"practical":[49],"problems":[50],"demand":[51],"maximum":[53],"with":[55,70,110],"not":[56],"much":[57],"cost":[58,112],"(expense).":[59],"For":[60],"example,":[61],"production":[63,76,130],"of":[64,81,87,146,161],"coal":[65,134,147,150],"mine":[66,151],"closely":[68],"correlated":[69],"security":[71,82],"in":[72,77,133,149],"that":[73],"it":[74],"increases":[75],"limited":[79],"range":[80],"situation.":[83],"On":[84],"base":[86],"Markov":[88,99],"decision":[89,100],"process":[90,101],"(MDP)":[91],"and":[92,114,131],"reinforcement":[93,103],"learning,":[94],"paper":[96,106,137],"introduced":[97],"constraint":[98,122,128],"into":[102],"learning.":[104],"The":[105,154],"improved":[107],"Q-learning":[108,118],"adding":[111],"factor":[113],"gave":[115],"new":[117],"based":[120],"on":[121],"MDP.":[123],"Finally,":[124],"according":[125],"between":[129],"safety":[132],"mine,":[135],"made":[138],"simulation":[140,155],"investigation":[141],"about":[142],"action":[144],"control":[145],"shearer":[148],"working":[152],"face.":[153],"result":[156],"had":[157],"verified":[158],"validity":[160],"method.":[163]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2131574156","counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2024-12-07T09:42:36.088029","created_date":"2016-06-24"}