{"id":"https://openalex.org/W4285600506","doi":"https://doi.org/10.24963/ijcai.2022/730","title":"On the Expressivity of Markov Reward (Extended Abstract)","display_name":"On the Expressivity of Markov Reward (Extended Abstract)","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285600506","doi":"https://doi.org/10.24963/ijcai.2022/730"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/730","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/730","pdf_url":"https://www.ijcai.org/proceedings/2022/0730.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0730.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080191195","display_name":"David Abel","orcid":"https://orcid.org/0000-0001-6311-9007"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Abel","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037981481","display_name":"Will Dabney","orcid":"https://orcid.org/0000-0003-4600-5520"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Will Dabney","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014267939","display_name":"Anna Harutyunyan","orcid":"https://orcid.org/0000-0002-5418-113X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anna Harutyunyan","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083477814","display_name":"Mark K. Ho","orcid":"https://orcid.org/0000-0002-1454-4768"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark K. Ho","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Brown University","Brown University {dmabel, wdabney,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]},{"raw_affiliation_string":"Brown University {dmabel, wdabney,","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Doina Precup","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046052093","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0001-9360-7060"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009722403"],"corresponding_institution_ids":["https://openalex.org/I175594653"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5254","last_page":"5258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10142","display_name":"Formal Methods in Verification","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9853000044822693,"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/computer-science","display_name":"Computer science","score":0.737091064453125},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.7127571105957031},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6959296464920044},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6789080500602722},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6470110416412354},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.566495418548584},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5611990690231323},{"id":"https://openalex.org/keywords/expressivity","display_name":"Expressivity","score":0.5207909941673279},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5135979652404785},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.47677117586135864},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4662325084209442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44130218029022217},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3345036506652832},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15550079941749573},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06845515966415405},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05226337909698486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737091064453125},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.7127571105957031},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6959296464920044},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6789080500602722},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6470110416412354},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.566495418548584},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5611990690231323},{"id":"https://openalex.org/C92811239","wikidata":"https://www.wikidata.org/wiki/Q20998670","display_name":"Expressivity","level":2,"score":0.5207909941673279},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5135979652404785},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.47677117586135864},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4662325084209442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44130218029022217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3345036506652832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15550079941749573},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06845515966415405},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05226337909698486},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/730","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/730","pdf_url":"https://www.ijcai.org/proceedings/2022/0730.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/730","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/730","pdf_url":"https://www.ijcai.org/proceedings/2022/0730.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.5299999713897705,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285600506.pdf","grobid_xml":"https://content.openalex.org/works/W4285600506.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W88199814","https://openalex.org/W1777239053","https://openalex.org/W2111116266","https://openalex.org/W2116671302","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2163602945","https://openalex.org/W2198041288","https://openalex.org/W2902143777","https://openalex.org/W3006334608","https://openalex.org/W4286882963","https://openalex.org/W4312236423"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2379651310"],"abstract_inverted_index":{"Reward":[0],"is":[1],"the":[2,14],"driving":[3],"force":[4],"for":[5],"reinforcement-learning":[6],"agents.":[7],"We":[8,33,90],"here":[9],"set":[10,46,94],"out":[11],"to":[12,22,31,108],"understand":[13],"expressivity":[15],"of":[16,42,47,73,79,95],"Markov":[17,85,101],"reward":[18,69,86,102,119],"as":[19],"a":[20,45,51,58,93,100],"way":[21],"capture":[23],"tasks":[24],"that":[25,67,83,98,104],"we":[26],"would":[27],"want":[28],"an":[29,106],"agent":[30,107],"perform.":[32],"frame":[34],"this":[35],"study":[36],"around":[37],"three":[38],"new":[39],"abstract":[40],"notions":[41],"\"task\":":[43],"(1)":[44],"acceptable":[48],"behaviors,":[49,55],"(2)":[50],"partial":[52,59],"ordering":[53,60],"over":[54,61],"or":[56],"(3)":[57],"trajectories.":[62],"Our":[63],"main":[64],"results":[65],"prove":[66],"while":[68],"can":[70,88],"express":[71],"many":[72],"these":[74],"tasks,":[75],"there":[76],"exist":[77],"instances":[78],"each":[80,110],"task":[81,111],"type":[82],"no":[84,117],"function":[87,103,120],"capture.":[89],"then":[91],"provide":[92],"polynomial-time":[96],"algorithms":[97],"construct":[99],"allows":[105],"perform":[109],"type,":[112],"and":[113],"correctly":[114],"determine":[115],"when":[116],"such":[118],"exists.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}