{"id":"https://openalex.org/W3152768544","doi":"https://doi.org/10.1145/3442381.3449862","title":"Match Plan Generation in Web Search with Parameterized Action Reinforcement Learning","display_name":"Match Plan Generation in Web Search with Parameterized Action Reinforcement Learning","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3152768544","doi":"https://doi.org/10.1145/3442381.3449862","mag":"3152768544"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3449862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449862","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3442381.3449862","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3442381.3449862","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081989147","display_name":"Ziyan Luo","orcid":"https://orcid.org/0000-0002-6091-0036"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyan Luo","raw_affiliation_strings":["Microsoft and University of California, San Diego, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft and University of California, San Diego, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035573979","display_name":"Linfeng Zhao","orcid":"https://orcid.org/0009-0007-0918-9777"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linfeng Zhao","raw_affiliation_strings":["Microsoft and Northeastern University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft and Northeastern University, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110801678","display_name":"Wei Cheng","orcid":"https://orcid.org/0000-0001-9532-4777"},"institutions":[{"id":"https://openalex.org/I153473198","display_name":"North China Electric Power University","ror":"https://ror.org/04qr5t414","country_code":"CN","type":"education","lineage":["https://openalex.org/I153473198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Cheng","raw_affiliation_strings":["Microsoft and North China Electric Power University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft and North China Electric Power University, China","institution_ids":["https://openalex.org/I153473198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101823159","display_name":"Sihao Chen","orcid":"https://orcid.org/0000-0003-2145-8021"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sihao Chen","raw_affiliation_strings":["Microsoft and University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft and University of California, Berkeley, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340161","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0002-3710-5979"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016088379","display_name":"Hui Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":["Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036415748","display_name":"Haidong Wang","orcid":"https://orcid.org/0000-0002-4614-5817"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haidong Wang","raw_affiliation_strings":["Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116294179","display_name":"Chuanjie Liu","orcid":"https://orcid.org/0009-0004-5183-8150"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanjie Liu","raw_affiliation_strings":["Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438310","display_name":"Mao Yang","orcid":"https://orcid.org/0009-0009-6455-3898"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Yang","raw_affiliation_strings":["Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101985940","display_name":"Lintao Zhang","orcid":"https://orcid.org/0009-0005-7527-8183"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lintao Zhang","raw_affiliation_strings":["Microsoft, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1040","last_page":"1052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8176393508911133},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7973166704177856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183318138122559},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5739046335220337},{"id":"https://openalex.org/keywords/action-plan","display_name":"Action plan","score":0.5134438276290894},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4665866494178772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4255205988883972},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3898164629936218},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35707080364227295},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3331971764564514},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08829072117805481}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8176393508911133},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7973166704177856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183318138122559},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5739046335220337},{"id":"https://openalex.org/C2780210234","wikidata":"https://www.wikidata.org/wiki/Q422638","display_name":"Action plan","level":2,"score":0.5134438276290894},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4665866494178772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4255205988883972},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3898164629936218},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35707080364227295},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3331971764564514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08829072117805481},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442381.3449862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449862","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3442381.3449862","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3442381.3449862","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449862","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3442381.3449862","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3152768544.pdf","grobid_xml":"https://content.openalex.org/works/W3152768544.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1757796397","https://openalex.org/W2064675550","https://openalex.org/W2096937925","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2150355110","https://openalex.org/W2165150801","https://openalex.org/W2168359464","https://openalex.org/W2173248099","https://openalex.org/W2531355666","https://openalex.org/W2623491082","https://openalex.org/W2741122588","https://openalex.org/W2781726626","https://openalex.org/W2908064123","https://openalex.org/W2944306386","https://openalex.org/W2963099939","https://openalex.org/W2963312729","https://openalex.org/W2963616477","https://openalex.org/W2964001908","https://openalex.org/W2964209691","https://openalex.org/W2981037657"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W2752208001","https://openalex.org/W2391330504","https://openalex.org/W4230717917"],"abstract_inverted_index":{"To":[0],"achieve":[1],"good":[2],"result":[3],"quality":[4,200],"and":[5,50,76,102,139,169,205],"short":[6],"query":[7,209],"response":[8,210],"time,":[9],"search":[10,179],"engines":[11],"use":[12],"specific":[13],"match":[14,34,42,47,55,86,188],"plans":[15,56,189],"on":[16,223],"Inverted":[17],"Index":[18],"to":[19,63,114,146,154],"help":[20],"retrieve":[21],"a":[22,39,90,98,104,128,162],"small":[23],"set":[24],"of":[25,30,38,41,132,194,201,208],"relevant":[26],"documents":[27,202],"from":[28],"billions":[29],"web":[31,178],"pages.":[32],"A":[33],"plan":[35,87],"is":[36],"composed":[37],"sequence":[40],"rules,":[43],"which":[44,68],"contain":[45],"discrete":[46],"rule":[48],"types":[49],"continuous":[51],"stopping":[52],"quotas.":[53],"Currently,":[54],"are":[57,150],"manually":[58],"designed":[59],"by":[60,190],"experts":[61],"according":[62],"their":[64],"several":[65],"years\u2019":[66],"experience,":[67],"encounters":[69],"difficulty":[70],"in":[71,119,175],"dealing":[72],"with":[73,97,165,198,213],"heterogeneous":[74],"queries":[75,160],"varying":[77],"data":[78],"distribution.":[79],"In":[80,122],"this":[81,156],"work,":[82],"we":[83,125],"formulate":[84],"the":[85,117,133,151,176,185,199,221],"generation":[88],"as":[89,161],"Partially":[91],"Observable":[92],"Markov":[93],"Decision":[94],"Process":[95],"(POMDP)":[96],"parameterized":[99],"action":[100],"space,":[101],"propose":[103],"novel":[105],"reinforcement":[106,173],"learning":[107,163,174],"algorithm":[108],"Parameterized":[109],"Action":[110],"Soft":[111],"Actor-Critic":[112],"(PASAC)":[113],"effectively":[115],"enhance":[116],"exploration":[118],"both":[120],"spaces.":[121],"our":[123],"scene,":[124],"also":[126,219],"discover":[127],"skew":[129],"prioritizing":[130],"issue":[131],"original":[134],"Prioritized":[135,142],"Experience":[136,143],"Replay":[137,144],"(PER)":[138],"introduce":[140],"Stratified":[141],"(SPER)":[145],"address":[147],"it.":[148],"We":[149],"first":[152],"group":[153],"generalize":[155],"task":[157],"for":[158],"all":[159],"problem":[164],"zero":[166],"prior":[167],"knowledge":[168],"successfully":[170],"apply":[171],"deep":[172],"real":[177],"environment.":[180],"Our":[181,217],"approach":[182],"greatly":[183],"outperforms":[184],"well-designed":[186],"production":[187],"over":[191],"70%":[192],"reduction":[193,207],"index":[195],"block":[196],"accesses":[197],"almost":[203],"unchanged,":[204],"9%":[206],"time":[211],"even":[212],"model":[214],"inference":[215],"cost.":[216],"method":[218],"beats":[220],"baselines":[222],"some":[224],"open-source":[225],"benchmarks1.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}