{"id":"https://openalex.org/W3106764401","doi":"https://doi.org/10.1109/icstcc50638.2020.9259716","title":"Brief Survey of Model-Based Reinforcement Learning Techniques","display_name":"Brief Survey of Model-Based Reinforcement Learning Techniques","publication_year":2020,"publication_date":"2020-10-08","ids":{"openalex":"https://openalex.org/W3106764401","doi":"https://doi.org/10.1109/icstcc50638.2020.9259716","mag":"3106764401"},"language":"en","primary_location":{"id":"doi:10.1109/icstcc50638.2020.9259716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icstcc50638.2020.9259716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 24th International Conference on System Theory, Control and Computing (ICSTCC)","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/A5036169107","display_name":"Constantin-Valentin Pal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108695","display_name":"Gheorghe Asachi Technical University of Ia\u0219i","ror":"https://ror.org/014zxnz40","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210108695"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Constantin-Valentin Pal","raw_affiliation_strings":["Faculty of Automatic Control and Computer Engineering, \"Gheorghe Asachi\" Technical University of Ia\u0219i, Ia\u0219i, Romania"],"affiliations":[{"raw_affiliation_string":"Faculty of Automatic Control and Computer Engineering, \"Gheorghe Asachi\" Technical University of Ia\u0219i, Ia\u0219i, Romania","institution_ids":["https://openalex.org/I4210108695"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063576338","display_name":"Florin Leon","orcid":"https://orcid.org/0000-0002-1370-9145"},"institutions":[{"id":"https://openalex.org/I4210108695","display_name":"Gheorghe Asachi Technical University of Ia\u0219i","ror":"https://ror.org/014zxnz40","country_code":"RO","type":"education","lineage":["https://openalex.org/I4210108695"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Florin Leon","raw_affiliation_strings":["Faculty of Automatic Control and Computer Engineering, \"Gheorghe Asachi\" Technical University of Ia\u0219i, Ia\u0219i, Romania"],"affiliations":[{"raw_affiliation_string":"Faculty of Automatic Control and Computer Engineering, \"Gheorghe Asachi\" Technical University of Ia\u0219i, Ia\u0219i, Romania","institution_ids":["https://openalex.org/I4210108695"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036169107"],"corresponding_institution_ids":["https://openalex.org/I4210108695"],"apc_list":null,"apc_paid":null,"fwci":1.0605,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.82568807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"97"},"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":0.9914000034332275,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9699000120162964,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9050717949867249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7076488137245178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6716924905776978},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6096351146697998},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5259832739830017},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4360752999782562}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9050717949867249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7076488137245178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6716924905776978},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6096351146697998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5259832739830017},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4360752999782562},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icstcc50638.2020.9259716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icstcc50638.2020.9259716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 24th International Conference on System Theory, Control and Computing (ICSTCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1570233100","https://openalex.org/W1978099898","https://openalex.org/W2087617385","https://openalex.org/W2104733512","https://openalex.org/W2132083787","https://openalex.org/W2150468603","https://openalex.org/W2153039919","https://openalex.org/W2158349948","https://openalex.org/W2290354866","https://openalex.org/W2580909119","https://openalex.org/W2738675347","https://openalex.org/W2772709170","https://openalex.org/W2785389871","https://openalex.org/W2786928559","https://openalex.org/W2789824229","https://openalex.org/W2795843265","https://openalex.org/W2810754397","https://openalex.org/W2822752092","https://openalex.org/W2859967432","https://openalex.org/W2908064123","https://openalex.org/W2920362155","https://openalex.org/W2923762280","https://openalex.org/W2949571867","https://openalex.org/W2950471160","https://openalex.org/W2950564923","https://openalex.org/W2951266961","https://openalex.org/W2953708620","https://openalex.org/W2962872206","https://openalex.org/W2964915587","https://openalex.org/W2990747716","https://openalex.org/W2996726407","https://openalex.org/W2997896361","https://openalex.org/W3013618273","https://openalex.org/W3021208093","https://openalex.org/W3034956653","https://openalex.org/W3100789280","https://openalex.org/W3103559770","https://openalex.org/W3110466314","https://openalex.org/W3118210634","https://openalex.org/W4288289109","https://openalex.org/W4288319859","https://openalex.org/W4289294484","https://openalex.org/W4293396018","https://openalex.org/W4297797010","https://openalex.org/W4298174377","https://openalex.org/W4298206671","https://openalex.org/W4324106947","https://openalex.org/W6633971062","https://openalex.org/W6675999342","https://openalex.org/W6685726866","https://openalex.org/W6692405165","https://openalex.org/W6696324988","https://openalex.org/W6702989015","https://openalex.org/W6732665253","https://openalex.org/W6741519989","https://openalex.org/W6741940250","https://openalex.org/W6743806954","https://openalex.org/W6746177919","https://openalex.org/W6748519856","https://openalex.org/W6748554570","https://openalex.org/W6748638692","https://openalex.org/W6748817170","https://openalex.org/W6750253780","https://openalex.org/W6751494529","https://openalex.org/W6753183898","https://openalex.org/W6753264383","https://openalex.org/W6754471908","https://openalex.org/W6756256016","https://openalex.org/W6757184387","https://openalex.org/W6760405395","https://openalex.org/W6760681535","https://openalex.org/W6763990646","https://openalex.org/W6764053384","https://openalex.org/W6764214684","https://openalex.org/W6764724164","https://openalex.org/W6771787661","https://openalex.org/W6775522024","https://openalex.org/W6786990698","https://openalex.org/W6788072495"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Model-free":[0],"reinforcement":[1,12],"learning":[2,14],"(MFRL)":[3],"usually":[4],"has":[5,65],"better":[6,57],"asymptotic":[7],"performance":[8,55],"than":[9],"the":[10,48,53,87],"model-based":[11],"(MBRL)":[13],"algorithms,":[15],"especially":[16],"in":[17,37,45,67,92,102],"complex":[18,80],"environments.":[19],"But":[20],"MBRL":[21,49,63,93],"algorithms":[22,50,101],"are":[23,31],"very":[24],"often":[25],"much":[26],"more":[27],"sample-efficient,":[28],"and":[29,94],"sometimes":[30],"able":[32],"to":[33],"learn":[34],"control":[35,74],"tasks":[36],"just":[38],"a":[39],"handful":[40],"of":[41,100],"trials.":[42],"In":[43,60,82],"addition,":[44],"some":[46,97],"domains,":[47,70],"can":[51],"reach":[52],"MFRL":[54],"with":[56,79],"sample":[58],"efficiency.":[59],"recent":[61],"years,":[62],"research":[64],"increased":[66],"various":[68],"application":[69],"such":[71],"as":[72],"robot":[73],"tasks,":[75],"or":[76],"game":[77],"environments":[78],"observations.":[81],"this":[83,103],"paper,":[84],"we":[85],"review":[86],"most":[88],"popular":[89],"techniques":[90],"used":[91],"look":[95],"at":[96],"useful":[98],"classification":[99],"area.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}