{"id":"https://openalex.org/W2148051466","doi":"https://doi.org/10.1109/robio.2007.4522470","title":"A unifying framework for HAMs-family HRL methods","display_name":"A unifying framework for HAMs-family HRL methods","publication_year":2007,"publication_date":"2007-12-01","ids":{"openalex":"https://openalex.org/W2148051466","doi":"https://doi.org/10.1109/robio.2007.4522470","mag":"2148051466"},"language":"en","primary_location":{"id":"doi:10.1109/robio.2007.4522470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2007.4522470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100899230","display_name":"Xiaoqin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du Xiaoqin","raw_affiliation_strings":["College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei Province, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103676128","display_name":"LI Qing-hua","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Qinghua","raw_affiliation_strings":["College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei Province, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":null,"display_name":"Han Jianjun","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Jianjun","raw_affiliation_strings":["College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei Province, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"1978","last_page":"1982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7936980724334717},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7881219983100891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7867476940155029},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6165252923965454},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5818331241607666},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48290181159973145},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.47931113839149475},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47049450874328613},{"id":"https://openalex.org/keywords/homomorphism","display_name":"Homomorphism","score":0.4698796570301056},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44849467277526855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4383730888366699},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14913037419319153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1331876814365387}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7936980724334717},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7881219983100891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867476940155029},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6165252923965454},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5818331241607666},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48290181159973145},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.47931113839149475},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47049450874328613},{"id":"https://openalex.org/C4042151","wikidata":"https://www.wikidata.org/wiki/Q215111","display_name":"Homomorphism","level":2,"score":0.4698796570301056},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44849467277526855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4383730888366699},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14913037419319153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1331876814365387},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio.2007.4522470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2007.4522470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1218520990","https://openalex.org/W1564393562","https://openalex.org/W1568042657","https://openalex.org/W1592847719","https://openalex.org/W2095770075","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2145739724","https://openalex.org/W6674618572"],"related_works":["https://openalex.org/W4308159138","https://openalex.org/W4327811209","https://openalex.org/W1979798674","https://openalex.org/W3169947911","https://openalex.org/W3037616202","https://openalex.org/W4388675521","https://openalex.org/W2108135022","https://openalex.org/W3148810651","https://openalex.org/W2789077243","https://openalex.org/W2898772359"],"abstract_inverted_index":{"In":[0,68,105],"the":[1,25,30,38,51,70,77],"HRL":[2],"(hierarchical":[3,15],"reinforcement":[4],"learning)":[5],"field,":[6],"there":[7],"are":[8],"three":[9],"main":[10],"methods":[11,21],"such":[12],"as":[13],"HAMs":[14,141],"abstract":[16],"machines),":[17],"options,":[18],"MAXQ.":[19],"These":[20],"all":[22],"rely":[23],"on":[24,122,135],"theory":[26],"of":[27,45,53,66,86],"SMDPs.":[28],"While":[29],"SMDP":[31,71],"framework":[32,72,130],"allows":[33],"us":[34,92],"to":[35,93,110],"directly":[36],"model":[37],"high-level":[39],"actions":[40],"that":[41],"take":[42],"varying":[43],"amounts":[44],"time,":[46],"it":[47],"provides":[48],"little":[49],"in":[50],"way":[52],"concrete":[54],"representational":[55],"guidance,":[56],"which":[57,88],"is":[58,89],"critical":[59],"from":[60],"a":[61,84,119,128],"computational":[62],"and":[63,97,115,149],"analytical":[64],"point":[65],"view.":[67],"particular,":[69],"does":[73],"not":[74],"specify":[75],"how":[76],"overall":[78],"task":[79],"can":[80,139,150],"be":[81],"decomposed":[82],"into":[83],"collection":[85],"subtasks,":[87],"important":[90],"for":[91,100,118,131,146],"do":[94],"state":[95,147],"abstraction":[96,148],"subtask":[98,102],"sharing":[99],"individual":[101],"or":[103,142],"module.":[104],"addition,":[106],"we":[107,138],"also":[108,151],"want":[109],"choose":[111],"between":[112],"hierarchical":[113],"optimality":[114,117],"recursive":[116],"given":[120],"hierarchy":[121],"our":[123],"problem.":[124],"This":[125],"paper":[126],"introduces":[127],"unifying":[129],"HAMs-family":[132],"methods.":[133],"Based":[134],"this":[136],"framework,":[137],"define":[140],"sub-":[143],"HAM":[144],"homomorphism":[145],"freely":[152],"select":[153],"alternative":[154],"policy":[155],"optimality.":[156]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}