{"id":"https://openalex.org/W3132553597","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533317","title":"Structure and Randomness in Planning and Reinforcement Learning","display_name":"Structure and Randomness in Planning and Reinforcement Learning","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3132553597","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533317","mag":"3132553597"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5087092802","display_name":"Konrad Czechowski","orcid":"https://orcid.org/0000-0002-9384-1137"},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Konrad Czechowski","raw_affiliation_strings":["Faculty of Mathematics, Informatics and Mechanics, University of Warsaw"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, Informatics and Mechanics, University of Warsaw","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075969995","display_name":"Piotr Januszewski","orcid":null},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]},{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Piotr Januszewski","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology","Faculty of Mathematics, Informatics and Mechanics, University of Warsaw"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology","institution_ids":["https://openalex.org/I169333911"]},{"raw_affiliation_string":"Faculty of Mathematics, Informatics and Mechanics, University of Warsaw","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031843495","display_name":"Piotr Kozakowski","orcid":null},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Piotr Kozakowski","raw_affiliation_strings":["Faculty of Mathematics, Informatics and Mechanics, University of Warsaw"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, Informatics and Mechanics, University of Warsaw","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055195176","display_name":"\u0141ukasz Kuci\u0144ski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120266","display_name":"Czech Academy of Sciences, Institute of Mathematics","ror":"https://ror.org/02tv1yf50","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210120266"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukasz Kucinski","raw_affiliation_strings":["Institute of Mathematics, Polish Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics, Polish Academy of Science","institution_ids":["https://openalex.org/I4210120266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089671067","display_name":"Piotr Mi\u0142o\u015b","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120266","display_name":"Czech Academy of Sciences, Institute of Mathematics","ror":"https://ror.org/02tv1yf50","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210120266"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Piotr Milos","raw_affiliation_strings":["Institute of Mathematics, Polish Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Mathematics, Polish Academy of Science","institution_ids":["https://openalex.org/I4210120266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58811308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4630","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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/T11574","display_name":"Artificial Intelligence in Games","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9858999848365784,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9769999980926514,"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":0.7118639349937439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7032579779624939},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.6473208665847778},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5829476118087769},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5810927748680115},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.5657427906990051},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5449823141098022},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.5161164999008179},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46801674365997314},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.46574270725250244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350464940071106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43447792530059814},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.3915063738822937},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34763723611831665},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24262389540672302},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17290151119232178},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11856448650360107}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7118639349937439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7032579779624939},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.6473208665847778},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5829476118087769},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5810927748680115},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.5657427906990051},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5449823141098022},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.5161164999008179},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46801674365997314},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.46574270725250244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350464940071106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43447792530059814},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3915063738822937},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34763723611831665},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24262389540672302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17290151119232178},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11856448650360107},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W112666333","https://openalex.org/W1588241099","https://openalex.org/W1714211023","https://openalex.org/W1863869622","https://openalex.org/W1969483458","https://openalex.org/W1991572458","https://openalex.org/W2107549951","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2123459560","https://openalex.org/W2126316555","https://openalex.org/W2126677653","https://openalex.org/W2145224651","https://openalex.org/W2147750403","https://openalex.org/W2151210636","https://openalex.org/W2290354866","https://openalex.org/W2410617946","https://openalex.org/W2589349991","https://openalex.org/W2618097077","https://openalex.org/W2738669288","https://openalex.org/W2738675347","https://openalex.org/W2766447205","https://openalex.org/W2766688757","https://openalex.org/W2890346000","https://openalex.org/W2902907165","https://openalex.org/W2920362155","https://openalex.org/W2950471160","https://openalex.org/W2960567166","https://openalex.org/W2962872206","https://openalex.org/W2962893049","https://openalex.org/W2963243556","https://openalex.org/W2963642149","https://openalex.org/W2963794592","https://openalex.org/W2963960193","https://openalex.org/W2964220198","https://openalex.org/W2964295739","https://openalex.org/W2989847975","https://openalex.org/W2993335716","https://openalex.org/W2995976796","https://openalex.org/W2996558468","https://openalex.org/W2997502221","https://openalex.org/W3035700320","https://openalex.org/W3102923851","https://openalex.org/W3118210634","https://openalex.org/W3136620014","https://openalex.org/W3145128584","https://openalex.org/W3164818296","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4246219036","https://openalex.org/W4287991549","https://openalex.org/W4288638482","https://openalex.org/W4293396018","https://openalex.org/W4297664295","https://openalex.org/W4297789121","https://openalex.org/W4298206671","https://openalex.org/W6604566608","https://openalex.org/W6637441126","https://openalex.org/W6678592152","https://openalex.org/W6682314434","https://openalex.org/W6696324988","https://openalex.org/W6738855998","https://openalex.org/W6740836278","https://openalex.org/W6741940250","https://openalex.org/W6745540326","https://openalex.org/W6751494529","https://openalex.org/W6754160304","https://openalex.org/W6757795073","https://openalex.org/W6760405395","https://openalex.org/W6765749921","https://openalex.org/W6771066560","https://openalex.org/W6779282036"],"related_works":["https://openalex.org/W2770627170","https://openalex.org/W4327811054","https://openalex.org/W2978000411","https://openalex.org/W4206302813","https://openalex.org/W2491631281","https://openalex.org/W1785631772","https://openalex.org/W2115503785","https://openalex.org/W2967025328","https://openalex.org/W2962865140","https://openalex.org/W4322703856"],"abstract_inverted_index":{"Planning":[0],"in":[1,82],"large":[2],"state":[3],"spaces":[4],"inevitably":[5],"needs":[6],"to":[7,46,79],"balance":[8],"the":[9,14,22,72,75,83,98],"depth":[10],"and":[11,27,66],"breadth":[12],"of":[13,24,100],"search.":[15],"It":[16,69],"has":[17],"a":[18,25,35],"crucial":[19],"impact":[20],"on":[21,89],"performance":[23],"planner":[26],"most":[28],"manage":[29],"this":[30,48],"interplay":[31],"implicitly.":[32],"We":[33],"present":[34],"novel":[36],"method":[37],"Shoot":[38],"Tree":[39],"Search":[40],"(STS),":[41],"which":[42],"makes":[43],"it":[44],"possible":[45],"control":[47,74],"trade-off":[49],"more":[50],"explicitly.":[51],"Our":[52],"algorithm":[53],"can":[54,96],"be":[55],"understood":[56],"as":[57],"an":[58],"interpolation":[59],"between":[60],"two":[61],"celebrated":[62],"search":[63,85],"mechanisms:":[64],"MCTS":[65],"random":[67],"shooting.":[68],"also":[70],"lets":[71],"user":[73],"bias-variance":[76],"trade-off,":[77],"akin":[78],"TD(n),":[80],"but":[81],"tree":[84],"context.":[86],"In":[87],"experiments":[88],"challenging":[90],"domains,":[91],"we":[92],"show":[93],"that":[94],"STS":[95],"get":[97],"best":[99],"both":[101],"worlds":[102],"consistently":[103],"achieving":[104],"higher":[105],"scores.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}