{"id":"https://openalex.org/W3172979527","doi":null,"title":"Reinforcement Learning for Cost-Aware Markov Decision Processes","display_name":"Reinforcement Learning for Cost-Aware Markov Decision Processes","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3172979527","mag":"3172979527"},"language":"en","primary_location":{"id":"mag:3172979527","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v139/suttle21a/suttle21a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5056599663","display_name":"Wesley A. Suttle","orcid":"https://orcid.org/0000-0003-1234-7151","observed_orcids":["https://orcid.org/0000-0003-1234-7151"]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wesley A. Suttle","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":"https://orcid.org/0000-0003-1234-7151","affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581","observed_orcids":["https://orcid.org/0000-0002-7446-7581"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign/MIT"],"raw_orcid":"https://orcid.org/0000-0002-7446-7581","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign/MIT","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727948","display_name":"Zhuoran Yang","orcid":"https://orcid.org/0000-0001-5269-9958","observed_orcids":["https://orcid.org/0000-0001-5269-9958"]},"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":"Zhuoran Yang","raw_affiliation_strings":["Princeton University"],"raw_orcid":"https://orcid.org/0000-0001-5269-9958","affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396338","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0003-2871-9888","observed_orcids":["https://orcid.org/0000-0003-2871-9888"]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":"https://orcid.org/0000-0003-2871-9888","affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076286694","display_name":"David N. Kraemer","orcid":"https://orcid.org/0000-0001-8621-199X","observed_orcids":["https://orcid.org/0000-0001-8621-199X"]},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David N. Kraemer","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1865,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.36302796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"9989","last_page":"9999"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00019999999494757503,"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/T12072","display_name":"Machine Learning and Algorithms","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/reinforcement-learning","display_name":"reinforcement learning","score":0.7739999890327454},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9229999780654907},{"id":"https://openalex.org/keywords/cost-sensitive-learning","display_name":"cost-sensitive learning","score":0.5600000023841858},{"id":"https://openalex.org/keywords/cost-minimization","display_name":"cost minimization","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8507891297340393},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7831887006759644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7179630994796753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.496387779712677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4579625725746155},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4326433837413788},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.095887690782547},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3172979527","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v139/suttle21a/suttle21a.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1777239053","https://openalex.org/W1845972764","https://openalex.org/W1968115484","https://openalex.org/W2027579135","https://openalex.org/W2070570138","https://openalex.org/W2094387729","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2148654185","https://openalex.org/W2154190222","https://openalex.org/W2154204727","https://openalex.org/W2155027007","https://openalex.org/W2161270100","https://openalex.org/W2169015875","https://openalex.org/W2172968643","https://openalex.org/W2332498091","https://openalex.org/W2618318883","https://openalex.org/W2914920107","https://openalex.org/W2940910199","https://openalex.org/W2960531549","https://openalex.org/W2963082979","https://openalex.org/W2966735560","https://openalex.org/W2970154960","https://openalex.org/W2970927156","https://openalex.org/W3003533476","https://openalex.org/W3034039613","https://openalex.org/W3101487584","https://openalex.org/W3101517963"],"related_works":["https://openalex.org/W3158548275","https://openalex.org/W3211465897","https://openalex.org/W2946019081","https://openalex.org/W6931904638","https://openalex.org/W2770826124","https://openalex.org/W7097098134","https://openalex.org/W3167017381","https://openalex.org/W7070837699","https://openalex.org/W7098044443","https://openalex.org/W4297728898"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2021-06-22T00:00:00"}