{"id":"https://openalex.org/W2894991981","doi":null,"title":"Q-map: a Convolutional Approach for Goal-Oriented Reinforcement Learning","display_name":"Q-map: a Convolutional Approach for Goal-Oriented Reinforcement Learning","alternate_titles":[],"publication_year":2018,"publication_date":"2018-09-27","ids":{"openalex":"https://openalex.org/W2894991981","mag":"2894991981"},"language":"en","primary_location":{"id":"mag:2894991981","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=rye7XnRqFm","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"parent_works":[],"lineage":["https://openalex.org/W2894991981"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10044/1/71861","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061689298","display_name":"Fabio Pardo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Fabio Pardo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542795","display_name":"Vitaly Levdik","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Vitaly Levdik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036281885","display_name":"Petar S. Kormushev","orcid":"https://orcid.org/0000-0002-6677-3044","observed_orcids":["https://orcid.org/0000-0002-6677-3044"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Petar Kormushev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3264,"has_fulltext":true,"cited_by_count":6,"reviewed_by_count":0,"citation_normalized_percentile":{"value":0.60917441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/autoencoder","display_name":"autoencoder","score":0.41499999165534973},{"id":"https://openalex.org/keywords/goal-selection","display_name":"goal selection","score":0.6880000233650208},{"id":"https://openalex.org/keywords/atari-games","display_name":"Atari games","score":0.5619999766349792},{"id":"https://openalex.org/keywords/montezuma-s-revenge","display_name":"Montezuma's Revenge","score":0.9390000104904175},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.31700000166893005},{"id":"https://openalex.org/keywords/value-function-estimation","display_name":"value function estimation","score":0.4490000009536743}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8001296520233154},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7954187393188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7568738460540771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367528200149536},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.4673573970794678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3993188142776489},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3433389663696289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12983357906341553},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11486172676086426},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2894991981","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=rye7XnRqFm","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/71861","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/71861","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working Paper"}],"best_oa_location":{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/71861","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/71861","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working Paper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2894991981.pdf","grobid_xml":"https://content.openalex.org/works/W2894991981.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W172298727","https://openalex.org/W567721252","https://openalex.org/W779494576","https://openalex.org/W1515851193","https://openalex.org/W1554015367","https://openalex.org/W2000514530","https://openalex.org/W2034806191","https://openalex.org/W2101524054","https://openalex.org/W2115211925","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2402144811","https://openalex.org/W2540700018","https://openalex.org/W2561776174","https://openalex.org/W2614839826","https://openalex.org/W2733961795","https://openalex.org/W2737215407","https://openalex.org/W2785542505","https://openalex.org/W2963276097","https://openalex.org/W2964121744","https://openalex.org/W3037207827","https://openalex.org/W3037932933","https://openalex.org/W7124150245"],"related_works":["https://openalex.org/W2998211224","https://openalex.org/W1755169537","https://openalex.org/W2809713945","https://openalex.org/W2111412461","https://openalex.org/W4403458696","https://openalex.org/W4409385787","https://openalex.org/W3140225428","https://openalex.org/W7124166422","https://openalex.org/W4296512964","https://openalex.org/W4312912107"],"abstract_inverted_index":{"Goal-oriented":[0],"learning":[1,9,31,132],"has":[2],"become":[3],"a":[4,16,56,82,105,136,139,158,180,187,201,232],"core":[5],"concept":[6],"in":[7,75,104,138,191,217],"reinforcement":[8],"(RL),":[10],"extending":[11],"the":[12,30,73,96,120,165,173,218,222,228,238,241,246],"reward":[13],"signal":[14],"as":[15,23,66,69],"sole":[17],"way":[18],"to":[19,37,94,113,122,134,144,163],"define":[20],"tasks.":[21],"However,":[22],"parameterizing":[24],"value":[25],"functions":[26],"with":[27,115,157],"goals":[28,42,169],"increases":[29],"complexity,":[32],"efficiently":[33,155],"reusing":[34],"past":[35],"experience":[36],"update":[38,164],"estimates":[39,166],"towards":[40,101,167,209],"several":[41,206],"at":[43,170,200],"once":[44],"becomes":[45],"desirable":[46],"but":[47],"usually":[48],"requires":[49],"independent":[50],"updates":[51],"per":[52],"goal.":[53],"Considering":[54],"that":[55,88,195],"significant":[57],"number":[58,98],"of":[59,72,99,161,183,193,227,240],"RL":[60],"environments":[61],"can":[62,153],"support":[63],"spatial":[64],"coordinates":[65],"goals,":[67],"such":[68],"on-screen":[70],"location":[71],"character":[74],"ATARI":[76],"or":[77],"SNES":[78],"games,":[79],"we":[80,185],"propose":[81,186],"novel":[83,188],"goal-oriented":[84],"agent":[85,121,175,230],"called":[86],"Q-map":[87,174,229],"utilizes":[89],"an":[90],"autoencoder-like":[91],"neural":[92],"network":[93,152],"predict":[95],"minimum":[97],"steps":[100,207,216],"each":[102],"coordinate":[103],"single":[106],"forward":[107],"pass.":[108],"This":[109],"architecture":[110],"is":[111],"similar":[112],"Horde":[114],"parameter":[116],"sharing":[117],"and":[118,128,213,224,235,251],"allows":[119],"discover":[123],"correlations":[124],"between":[125],"visual":[126],"patterns":[127],"navigation.":[129],"For":[130],"example":[131],"how":[133,150],"use":[135],"ladder":[137],"game":[140],"could":[141,176],"be":[142,154,177],"transferred":[143],"other":[145],"ladders":[146],"later.":[147],"We":[148,220],"show":[149],"this":[151],"trained":[156],"3D":[159],"variant":[160],"Q-learning":[162],"all":[168],"once.":[171],"While":[172],"used":[178],"for":[179],"wide":[181],"range":[182],"applications,":[184],"exploration":[189,243],"mechanism":[190,244],"place":[192],"epsilon-greedy":[194],"relies":[196],"on":[197,231,245],"goal":[198],"selection":[199],"desired":[202],"distance":[203],"followed":[204],"by":[205],"taken":[208],"it,":[210],"allowing":[211],"long":[212],"coherent":[214],"exploratory":[215],"environment.":[219],"demonstrate":[221,237],"accuracy":[223],"generalization":[225],"qualities":[226],"grid-world":[233],"environment":[234],"then":[236],"efficiency":[239],"proposed":[242],"notoriously":[247],"difficult":[248],"Montezuma's":[249],"Revenge":[250],"Super":[252],"Mario":[253],"All-Stars":[254],"games.":[255]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2894991981","counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2018-10-12T00:00:00"}
