{"id":"https://openalex.org/W4403210149","doi":"https://doi.org/10.1109/tce.2024.3476109","title":"Hands-Free: Action Abstraction With Hierarchical Reinforcement Learning in Text-Based Games","display_name":"Hands-Free: Action Abstraction With Hierarchical Reinforcement Learning in Text-Based Games","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403210149","doi":"https://doi.org/10.1109/tce.2024.3476109"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2024.3476109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2024.3476109","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-article"},"type":"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/A5081872546","display_name":"Anjie Zhu","orcid":"https://orcid.org/0000-0002-4634-7961"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anjie Zhu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101811641","display_name":"Hongcai He","orcid":"https://orcid.org/0000-0001-8813-1619"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongcai He","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongjun Yang","orcid":"https://orcid.org/0009-0001-9561-8764"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Yang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088728950","display_name":"Zetao Zheng","orcid":"https://orcid.org/0000-0002-7801-0378"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zetao Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072350518","display_name":"Jie Shao","orcid":"https://orcid.org/0000-0003-2615-1555"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Shao","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081872546"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.683,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75906189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"71","issue":"2","first_page":"5513","last_page":"5522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8806999921798706,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8806999921798706,"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":0.8230999708175659,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7620000243186951,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.693706214427948},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.681032121181488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6741054058074951},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5312960743904114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45241260528564453},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4465847611427307},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4255217909812927},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3928464651107788},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19781631231307983}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.693706214427948},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.681032121181488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6741054058074951},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5312960743904114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45241260528564453},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4465847611427307},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4255217909812927},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3928464651107788},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19781631231307983},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2024.3476109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2024.3476109","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1882737025","display_name":null,"funder_award_id":"62276047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5790304657","display_name":null,"funder_award_id":"2024JDRC0055","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1934909785","https://openalex.org/W2109910161","https://openalex.org/W2250539671","https://openalex.org/W2883318486","https://openalex.org/W2902391430","https://openalex.org/W2964179661","https://openalex.org/W2964199361","https://openalex.org/W2964227312","https://openalex.org/W2996887765","https://openalex.org/W2997475283","https://openalex.org/W2998557583","https://openalex.org/W3099204253","https://openalex.org/W3099954076","https://openalex.org/W3177151026","https://openalex.org/W3199912944","https://openalex.org/W3200711617","https://openalex.org/W4224293203","https://openalex.org/W4297964528","https://openalex.org/W4321524193","https://openalex.org/W4379033766","https://openalex.org/W4385945558","https://openalex.org/W4386566906","https://openalex.org/W4387407043","https://openalex.org/W4392940570"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Large-scale":[0],"knowledge":[1,88],"discovery":[2],"and":[3,33,43,54,60,64,89,143,168,177],"decision-making":[4],"based":[5,106],"on":[6,51,74,80,107,174],"textual":[7,20,55],"data":[8,21],"are":[9],"crucial":[10],"in":[11,190,193],"consumer":[12,194],"electronics.":[13,195],"For":[14],"instance,":[15],"intelligent":[16],"home":[17,31],"robots":[18],"analyze":[19],"to":[22,26,68,102,116,158],"tailor":[23],"household":[24],"tasks":[25,128],"user":[27],"preferences,":[28],"enhancing":[29,191],"smart":[30],"convenience":[32],"comfort.":[34],"Text-based":[35],"games":[36,49,176],"offer":[37],"a":[38,97,154],"research":[39],"platform":[40],"for":[41,148],"testing":[42],"developing":[44],"artificial":[45],"intelligence":[46,192],"algorithms.":[47],"These":[48],"rely":[50],"written":[52],"narratives":[53],"interactions":[56],"while":[57],"presenting":[58],"large":[59,142],"combinational":[61],"action":[62,99,145],"space,":[63],"partial":[65,149],"observability":[66,150],"issues":[67],"agents.":[69],"However,":[70],"previous":[71],"methods":[72],"relied":[73],"pre-specifying":[75],"the":[76,108,138,164,178,181],"subtasks":[77,132],"or":[78,133],"pre-training":[79],"datasets":[81],"derived":[82],"from":[83],"human":[84],"gameplay,":[85],"requiring":[86],"prior":[87],"manual":[90],"configuration.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95,152],"introduce":[96],"novel":[98],"abstraction":[100],"method":[101],"free":[103],"our":[104,124,184],"hands":[105],"option":[109],"framework,":[110,186],"which":[111],"uses":[112],"temporally":[113],"extended":[114],"macro-actions":[115],"encapsulate":[117],"relevant":[118],"long-horizon":[119],"behaviors.":[120],"Through":[121],"leveraging":[122],"options,":[123],"framework":[125],"decomposes":[126],"complex":[127],"autonomously":[129],"without":[130],"pre-specified":[131],"demonstrations,":[134],"thereby":[135],"partially":[136],"alleviating":[137],"obstacles":[139],"posed":[140],"by":[141],"combinatorial":[144],"spaces.":[146],"Moreover,":[147],"issue,":[151],"employ":[153],"bi-directional":[155],"attention":[156],"mechanism":[157],"estimate":[159],"state-action":[160],"value":[161],"accurately,":[162],"strengthening":[163],"interdependence":[165],"between":[166],"state":[167],"action.":[169],"We":[170],"conduct":[171],"extensive":[172],"experiments":[173],"text-based":[175],"results":[179],"show":[180],"effectiveness":[182],"of":[183],"proposed":[185],"highlighting":[187],"its":[188],"potential":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
