{"id":"https://openalex.org/W3036846812","doi":"https://doi.org/10.1109/tcyb.2021.3102510","title":"Parameterized MDPs and Reinforcement Learning Problems\u2014A Maximum Entropy Principle-Based Framework","display_name":"Parameterized MDPs and Reinforcement Learning Problems\u2014A Maximum Entropy Principle-Based Framework","publication_year":2021,"publication_date":"2021-08-18","ids":{"openalex":"https://openalex.org/W3036846812","doi":"https://doi.org/10.1109/tcyb.2021.3102510","mag":"3036846812","pmid":"https://pubmed.ncbi.nlm.nih.gov/34406959"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2021.3102510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3102510","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"preprint","indexed_in":["crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/523892","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103142073","display_name":"Amber Srivastava","orcid":"https://orcid.org/0000-0002-0568-8276"},"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":true,"raw_author_name":"Amber Srivastava","raw_affiliation_strings":["Mechanical Science and Engineering Department and Coordinated Science Laboratory, University of Illinois at Urbana–Champaign, Urbana, IL, USA","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Mechanical Science and Engineering Department and Coordinated Science Laboratory, University of Illinois at Urbana–Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051680600","display_name":"Srinivasa M. Salapaka","orcid":"https://orcid.org/0000-0002-3259-6027"},"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":"Srinivasa M. Salapaka","raw_affiliation_strings":["Mechanical Science and Engineering Department and Coordinated Science Laboratory, University of Illinois at Urbana–Champaign, Urbana, IL, USA","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Mechanical Science and Engineering Department and Coordinated Science Laboratory, University of Illinois at Urbana–Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103142073"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00628377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"52","issue":"9","first_page":"9339","last_page":"9351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8165108561515808},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8022024631500244},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.7831676006317139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503850221633911},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5848392844200134},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5667991638183594},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.5524420738220215},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5437459349632263},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5305942296981812},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5176497101783752},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48521068692207336},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.45285868644714355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32769775390625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2835959196090698},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17659059166908264}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8165108561515808},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8022024631500244},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.7831676006317139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503850221633911},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5848392844200134},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5667991638183594},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.5524420738220215},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5437459349632263},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5305942296981812},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5176497101783752},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48521068692207336},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.45285868644714355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32769775390625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2835959196090698},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17659059166908264},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1109/tcyb.2021.3102510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3102510","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:34406959","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34406959","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/523892","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/523892","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE Transactions on Cybernetics, 52 (9)","raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"mag:3036846812","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2006.09646","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.2006.09646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.09646","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.3929/ethz-b-000523892","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000523892","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/523892","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/523892","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE Transactions on Cybernetics, 52 (9)","raw_type":"info:eu-repo/semantics/acceptedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1664178993","display_name":null,"funder_award_id":"DE-EE0009125","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7831170967","display_name":null,"funder_award_id":"18-30639","funder_id":"https://openalex.org/F4320337392","funder_display_name":"Division of Electrical, Communications and Cyber Systems"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309369","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44"},{"id":"https://openalex.org/F4320322211","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49"},{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320332500","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W76530103","https://openalex.org/W1499669280","https://openalex.org/W1504244604","https://openalex.org/W1509562192","https://openalex.org/W1516418405","https://openalex.org/W1522099992","https://openalex.org/W1576452626","https://openalex.org/W1745373831","https://openalex.org/W1771410628","https://openalex.org/W1941445455","https://openalex.org/W1951602908","https://openalex.org/W1974307281","https://openalex.org/W1980648727","https://openalex.org/W1998783985","https://openalex.org/W2019064215","https://openalex.org/W2022918053","https://openalex.org/W2032558547","https://openalex.org/W2057898911","https://openalex.org/W2070469928","https://openalex.org/W2077085434","https://openalex.org/W2098774185","https://openalex.org/W2103718624","https://openalex.org/W2108711094","https://openalex.org/W2112492957","https://openalex.org/W2115211925","https://openalex.org/W2121110499","https://openalex.org/W2142477416","https://openalex.org/W2143072483","https://openalex.org/W2157174816","https://openalex.org/W2168839459","https://openalex.org/W2169324952","https://openalex.org/W2180756958","https://openalex.org/W2253991908","https://openalex.org/W2256420211","https://openalex.org/W2400318990","https://openalex.org/W2402108766","https://openalex.org/W2560615388","https://openalex.org/W2593044849","https://openalex.org/W2619268125","https://openalex.org/W2752501126","https://openalex.org/W2781726626","https://openalex.org/W2787933113","https://openalex.org/W2897417898","https://openalex.org/W2912924301","https://openalex.org/W2949078258","https://openalex.org/W2949996623","https://openalex.org/W2952171869","https://openalex.org/W2962847657","https://openalex.org/W2963169817","https://openalex.org/W2963257680","https://openalex.org/W2963312729","https://openalex.org/W2965140792","https://openalex.org/W2971463999","https://openalex.org/W2986925736","https://openalex.org/W3027719445","https://openalex.org/W4299551239","https://openalex.org/W6638018090","https://openalex.org/W6674884181","https://openalex.org/W6677067356","https://openalex.org/W6681795105","https://openalex.org/W6684985892","https://openalex.org/W6734206676","https://openalex.org/W6739455066","https://openalex.org/W6754843927","https://openalex.org/W6758608932","https://openalex.org/W6762529202"],"related_works":["https://openalex.org/W3194166078","https://openalex.org/W2963057120","https://openalex.org/W2912924301","https://openalex.org/W2899032397","https://openalex.org/W167970998","https://openalex.org/W3021426118","https://openalex.org/W2070469928","https://openalex.org/W2949078258","https://openalex.org/W2162401674","https://openalex.org/W2132096648","https://openalex.org/W2565610523","https://openalex.org/W2765274790","https://openalex.org/W2931553127","https://openalex.org/W2015482176","https://openalex.org/W3200847588","https://openalex.org/W3035793736","https://openalex.org/W2948104910","https://openalex.org/W2182995676","https://openalex.org/W3014860839","https://openalex.org/W2186942795"],"abstract_inverted_index":{"We":[0,41,227],"present":[1],"a":[2,6,96,104,209],"framework":[3,13,69,158],"to":[4,22,38,71,141,160,180,208,232,237],"address":[5],"class":[7,162],"of":[8,46,76,80,99,112,133,163,219],"sequential":[9,47],"decision-making":[10,48],"problems.":[11],"Our":[12],"features":[14],"learning":[15,118],"the":[16,26,77,81,84,88,100,110,117,131,161,177,182,187,192,216,223],"optimal":[17,183,189],"control":[18],"policy":[19,90,108],"with":[20,36,58,186,200],"robustness":[21,236],"noisy":[23,134,238],"data,":[24],"determining":[25],"unknown":[27],"state":[28],"and":[29,32,86,120,126,151,166,171,176,222,235],"action":[30],"parameters,":[31],"performing":[33],"sensitivity":[34,230],"analysis":[35],"respect":[37],"problem":[39,214,233],"parameters.":[40],"consider":[42],"two":[43],"broad":[44],"categories":[45],"problems":[49],"modeled":[50],"as":[51,136,145],"infinite":[52],"horizon":[53],"Markov":[54],"decision":[55],"processes":[56],"(MDPs)":[57],"(and":[59],"without)":[60],"an":[61],"absorbing":[62],"state.":[63],"The":[64,157],"central":[65],"idea":[66],"underlying":[67],"our":[68,139],"is":[70,179],"quantify":[72],"exploration":[73,113],"in":[74,116,130,138],"terms":[75],"Shannon":[78],"entropy":[79,152],"trajectories":[82],"under":[83],"MDP":[85,165],"determine":[87,181],"stochastic":[89],"that":[91],"maximizes":[92],"it":[93],"while":[94],"guaranteeing":[95],"low":[97],"value":[98],"expected":[101],"cost":[102,194],"along":[103,185],"trajectory.":[105],"This":[106],"resulting":[107],"enhances":[109],"quality":[111],"early":[114],"on":[115],"process,":[119],"consequently":[121],"allows":[122],"faster":[123],"convergence":[124],"rates":[125],"robust":[127],"solutions":[128],"even":[129],"presence":[132],"data":[135],"demonstrated":[137],"comparisons":[140],"popular":[142],"algorithms,":[143],"such":[144],"Q":[146,149,155],"-learning,":[147,150],"Double":[148],"regularized":[153],"Soft":[154],"-learning.":[156],"extends":[159],"parameterized":[164],"RL":[167],"problems,":[168],"where":[169],"states":[170],"actions":[172],"are":[173],"parameter":[174],"dependent,":[175],"objective":[178],"parameters":[184,234],"corresponding":[188],"policy.":[190],"Here,":[191],"associated":[193],"function":[195],"can":[196],"possibly":[197],"be":[198],"nonconvex":[199],"multiple":[201],"poor":[202],"local":[203],"minima.":[204],"Simulation":[205],"results":[206],"applied":[207],"5G":[210],"small":[211,224],"cell":[212,225],"network":[213],"demonstrate":[215],"successful":[217],"determination":[218],"communication":[220],"routes":[221],"locations.":[226],"also":[228],"obtain":[229],"measures":[231],"environment":[239],"data.":[240]},"counts_by_year":[],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}