{"id":"https://openalex.org/W3108895463","doi":null,"title":"Policy Supervectors: General Characterization of Agents by their Behaviour.","display_name":"Policy Supervectors: General Characterization of Agents by their Behaviour.","publication_year":2020,"publication_date":"2020-12-02","ids":{"openalex":"https://openalex.org/W3108895463","mag":"3108895463"},"language":"en","primary_location":{"id":"mag:3108895463","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2012.01244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2012.01244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048689678","display_name":"Anssi Kanervisto","orcid":"https://orcid.org/0000-0002-7479-4574","observed_orcids":["https://orcid.org/0000-0002-7479-4574"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anssi Kanervisto","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7479-4574","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322","observed_orcids":["https://orcid.org/0000-0002-4371-7322"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4371-7322","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003","observed_orcids":["https://orcid.org/0000-0002-5885-0003"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ville Hautam\u00e4ki","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5885-0003","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.0006000000284984708,"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":9.999999747378752e-05,"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/state-distribution","display_name":"state distribution","score":0.42500001192092896},{"id":"https://openalex.org/keywords/decision-making-agents","display_name":"decision-making agents","score":0.7149999737739563},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7850000262260437},{"id":"https://openalex.org/keywords/evolutionary-training","display_name":"evolutionary training","score":0.824999988079071},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/high-dimensional-state-spaces","display_name":"high-dimensional state spaces","score":0.6549999713897705}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7211049795150757},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7076099514961243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962720155715942},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5714200139045715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5089662075042725},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4748968183994293},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45613959431648254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42982152104377747},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08966109156608582},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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":"mag:3108895463","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2012.01244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3108895463","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2012.01244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1663973292","https://openalex.org/W1931877416","https://openalex.org/W1959608418","https://openalex.org/W1992402718","https://openalex.org/W2033178790","https://openalex.org/W2049633694","https://openalex.org/W2097571405","https://openalex.org/W2101234009","https://openalex.org/W2111935653","https://openalex.org/W2112036188","https://openalex.org/W2121863487","https://openalex.org/W2147147599","https://openalex.org/W2150468603","https://openalex.org/W2154022540","https://openalex.org/W2165180455","https://openalex.org/W2187089797","https://openalex.org/W2260756217","https://openalex.org/W2342840547","https://openalex.org/W2419612459","https://openalex.org/W2434014514","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2754517384","https://openalex.org/W2778749116","https://openalex.org/W2788741142","https://openalex.org/W2803926500","https://openalex.org/W2899205164","https://openalex.org/W2914261249","https://openalex.org/W2949608212","https://openalex.org/W2953319219","https://openalex.org/W2962779270","https://openalex.org/W2963790038","https://openalex.org/W3009007264","https://openalex.org/W3020277389","https://openalex.org/W3022566517","https://openalex.org/W3032398409","https://openalex.org/W3033564068","https://openalex.org/W3034296891","https://openalex.org/W3034692406","https://openalex.org/W3035080282","https://openalex.org/W3035403520","https://openalex.org/W3037207827","https://openalex.org/W3041929019","https://openalex.org/W3099437791","https://openalex.org/W3103078873","https://openalex.org/W3115502595","https://openalex.org/W3119486431","https://openalex.org/W3166968915","https://openalex.org/W6960125083"],"related_works":["https://openalex.org/W3208865810","https://openalex.org/W1523592794","https://openalex.org/W7130272045","https://openalex.org/W3128003752","https://openalex.org/W7097494111","https://openalex.org/W7096455153","https://openalex.org/W3213689373","https://openalex.org/W4220913687","https://openalex.org/W165608728","https://openalex.org/W7116937417"],"abstract_inverted_index":{"By":[0],"studying":[1,77,134],"the":[2,26,45,49,58,88,98,135,152,167],"underlying":[3],"policies":[4,107,123,138],"of":[5,47,71,90,100,109,122,137,155],"decision-making":[6],"agents,":[7],"we":[8],"can":[9,105],"learn":[10],"about":[11],"their":[12,110],"shortcomings":[13],"and":[14,118,144],"potentially":[15],"improve":[16],"them.":[17],"Traditionally,":[18],"this":[19],"has":[20],"been":[21],"done":[22],"either":[23],"by":[24,43,87,133],"examining":[25],"agent's":[27,162],"implementation,":[28],"its":[29,36],"behaviour":[30,60],"while":[31],"it":[32],"is":[33,74,158],"being":[34],"executed,":[35],"performance":[37],"with":[38],"a":[39,125],"reward/fitness":[40],"function":[41],"or":[42,65],"visualizing":[44],"density":[46],"states":[48,91],"agent":[50],"visits.":[51],"However,":[52],"these":[53],"methods":[54],"fail":[55],"to":[56,69,120],"describe":[57],"policy's":[59],"in":[61,161,166],"complex,":[62],"high-dimensional":[63],"environments":[64],"do":[66],"not":[67,164],"scale":[68,119],"thousands":[70,121],"policies,":[72],"which":[73],"required":[75],"when":[76],"training":[78,143],"algorithms.":[79],"We":[80,129],"propose":[81],"policy":[82],"supervectors":[83,104],"for":[84],"characterizing":[85],"agents":[86],"distribution":[89],"they":[92],"visit,":[93],"adopting":[94],"successful":[95],"techniques":[96],"from":[97],"area":[99],"speech":[101],"technology.":[102],"Policy":[103],"characterize":[106],"regardless":[108],"design":[111],"philosophy":[112],"(e.g.":[113],"rule-based":[114],"vs.":[115],"neural":[116],"networks)":[117],"on":[124,149],"single":[126],"workstation":[127],"machine.":[128],"demonstrate":[130],"method's":[131],"applicability":[132],"evolution":[136],"during":[139],"reinforcement":[140],"learning,":[141,146],"evolutionary":[142,156],"imitation":[145],"providing":[147],"insight":[148],"e.g.":[150],"how":[151],"search":[153],"space":[154],"algorithms":[157],"also":[159],"reflected":[160],"behaviour,":[163],"just":[165],"parameters.":[168]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-12-07T00:00:00"}