{"id":"https://openalex.org/W3107227009","doi":"https://doi.org/10.1109/iccp51029.2020.9266153","title":"Keynote Lecture: Building Knowledge For AI AgentsWith Reinforcement Learning","display_name":"Keynote Lecture: Building Knowledge For AI AgentsWith Reinforcement Learning","publication_year":2020,"publication_date":"2020-09-03","ids":{"openalex":"https://openalex.org/W3107227009","doi":"https://doi.org/10.1109/iccp51029.2020.9266153","mag":"3107227009"},"language":"en","primary_location":{"id":"doi:10.1109/iccp51029.2020.9266153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp51029.2020.9266153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-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/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA","GB"],"is_corresponding":true,"raw_author_name":"Doina Precup","raw_affiliation_strings":["McGill University and DeepMind,Canada","McGill University and DeepMind, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University and DeepMind,Canada","institution_ids":["https://openalex.org/I5023651","https://openalex.org/I4210090411"]},{"raw_affiliation_string":"McGill University and DeepMind, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065836447"],"corresponding_institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15382752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8309999704360962,"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":0.8309999704360962,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8594907522201538},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.6913109421730042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6596965789794922},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6318225860595703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5710479617118835},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5346640348434448},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42059704661369324},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3180795907974243},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1435318887233734}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8594907522201538},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.6913109421730042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596965789794922},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6318225860595703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5710479617118835},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5346640348434448},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42059704661369324},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3180795907974243},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1435318887233734},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp51029.2020.9266153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp51029.2020.9266153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W2295809616","https://openalex.org/W2501594388","https://openalex.org/W1559800691","https://openalex.org/W2417026147","https://openalex.org/W164263582","https://openalex.org/W2969867523"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,67,124,135,139,176],"allows":[2],"autonomous":[3],"agents":[4,77,140,177],"to":[5,8,43,46,81,101,129,173,183,189],"learn":[6,44],"how":[7,45,172],"act":[9,47],"in":[10,23,29,38,75,91,123],"a":[11,51,69,88],"stochastic,":[12],"unknown":[13],"environment,":[14,186],"with":[15],"which":[16,39],"they":[17],"can":[18,141,162],"interact.":[19],"Deep":[20],"reinforcement":[21,66,92,138,175],"learning,":[22,93],"particular,":[24],"has":[25,42],"achieved":[26],"great":[27],"success":[28,53],"well-defined":[30],"application":[31],"domains,":[32],"such":[33],"as":[34,68],"Go":[35],"or":[36],"chess,":[37],"an":[40],"agent":[41],"and":[48,97,118,154],"there":[49],"is":[50,80,180],"clear":[52],"criterion.":[54],"In":[55,127],"this":[56],"talk,":[57],"I":[58,85,108,166],"will":[59,86,109,167],"focus":[60],"on":[61],"the":[62,94,112,131,143,169],"potential":[63],"role":[64,113],"of":[65,105,114,134,145,150,152,171],"tool":[70],"for":[71],"building":[72],"knowledge":[73,136,191],"representations":[74],"AI":[76],"whose":[78,178],"goal":[79,179],"perform":[82],"continual":[83],"learning.":[84],"examine":[87],"key":[89],"concept":[90],"value":[95],"function,":[96],"discuss":[98,111,168],"its":[99],"generalization":[100],"support":[102],"various":[103],"forms":[104],"predictive":[106,121],"knowledge.":[107,126],"also":[110,188],"temporally":[115],"extended":[116],"actions,":[117],"their":[119,185,193],"associated":[120],"models,":[122],"procedural":[125],"order":[128],"tame":[130],"possible":[132],"complexity":[133],"representations,":[137],"use":[142],"concepts":[144],"intents":[146],"(ie":[147],"intended":[148],"consequences":[149],"courses":[151],"actions)":[153],"affordances":[155],"(which":[156],"capture":[157],"knowlege":[158],"about":[159,192],"where":[160],"actions":[161],"be":[163],"applied).":[164],"Finally,":[165],"challenge":[170],"evaluate":[174],"not":[181],"just":[182],"control":[184],"but":[187],"build":[190],"world.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}