{"id":"https://openalex.org/W4389665391","doi":"https://doi.org/10.1109/iros55552.2023.10341599","title":"Offline Reinforcement Learning for Quadrotor Control: Overcoming the Ground Effect","display_name":"Offline Reinforcement Learning for Quadrotor Control: Overcoming the Ground Effect","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665391","doi":"https://doi.org/10.1109/iros55552.2023.10341599"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341599","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5014244451","display_name":"Luca Sacchetto","orcid":"https://orcid.org/0009-0009-6718-1452"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Luca Sacchetto","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056950047","display_name":"Mathias Korte","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mathias Korte","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020980906","display_name":"Sven Gronauer","orcid":"https://orcid.org/0000-0002-0047-5116"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Gronauer","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033656694","display_name":"Matthias Kissel","orcid":"https://orcid.org/0000-0003-4089-3934"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Kissel","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074346065","display_name":"Klaus Diepold","orcid":"https://orcid.org/0000-0003-0439-7511"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Diepold","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014244451"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58712536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"7539","last_page":"7544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919000267982483,"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":0.9919000267982483,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9902999997138977,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9188732504844666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7004525661468506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5566241145133972},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.49265581369400024},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4764935374259949},{"id":"https://openalex.org/keywords/transfer-problem","display_name":"Transfer problem","score":0.45026707649230957},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4490832984447479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4244995713233948}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9188732504844666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004525661468506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5566241145133972},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.49265581369400024},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4764935374259949},{"id":"https://openalex.org/C2779066501","wikidata":"https://www.wikidata.org/wiki/Q1761267","display_name":"Transfer problem","level":2,"score":0.45026707649230957},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4490832984447479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4244995713233948},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341599","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":33,"referenced_works":["https://openalex.org/W2465948386","https://openalex.org/W2736601468","https://openalex.org/W2891629144","https://openalex.org/W2901402208","https://openalex.org/W2947150733","https://openalex.org/W2963184939","https://openalex.org/W3003669699","https://openalex.org/W3010612407","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3088310808","https://openalex.org/W3099548126","https://openalex.org/W3120778962","https://openalex.org/W3122115432","https://openalex.org/W3156063639","https://openalex.org/W3176539729","https://openalex.org/W3190079665","https://openalex.org/W3202883604","https://openalex.org/W3211444363","https://openalex.org/W4200438872","https://openalex.org/W4285077530","https://openalex.org/W4287756699","https://openalex.org/W4288363736","https://openalex.org/W4312992339","https://openalex.org/W6756581457","https://openalex.org/W6763704811","https://openalex.org/W6779265984","https://openalex.org/W6787971688","https://openalex.org/W6794595143","https://openalex.org/W6802659552","https://openalex.org/W6804112224","https://openalex.org/W6839744550","https://openalex.org/W6846223737"],"related_works":["https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650","https://openalex.org/W2091421219","https://openalex.org/W2158618075","https://openalex.org/W4312257007","https://openalex.org/W3157032506","https://openalex.org/W3096255544","https://openalex.org/W3158006613","https://openalex.org/W2745420784"],"abstract_inverted_index":{"Applying":[0],"Reinforcement":[1,71,150],"Learning":[2,72,151],"to":[3,24,35,44,77,81,132,138],"solve":[4],"real-world":[5,141],"optimization":[6],"problems":[7,99],"presents":[8],"significant":[9],"challenges":[10],"because":[11],"of":[12,16,69,88,117,124],"the":[13,26,33,36,47,67,86,95,114,118,122,128,134],"large":[14],"amount":[15],"data":[17],"normally":[18],"required.":[19],"A":[20],"popular":[21,125],"solution":[22],"is":[23,50],"train":[25],"algorithms":[27,152],"in":[28,54,100,161],"a":[29,74,89,140,154],"simulation":[30],"and":[31,59,121,157],"transfer":[32,80,126],"weights":[34],"real":[37],"system.":[38],"However,":[39],"sim-to-real":[40,78,105,108],"approaches":[41],"are":[42],"prone":[43],"fail":[45,131],"when":[46],"Reality":[48],"Gap":[49],"too":[51],"big,":[52],"e.g.":[53],"robotic":[55],"systems":[56],"with":[57,113],"complex":[58],"non-linear":[60],"dynamics.":[61],"In":[62],"this":[63,162],"work,":[64],"we":[65,92,145],"propose":[66],"use":[68,163],"Offline":[70,149],"as":[73],"viable":[75],"alternative":[76,160],"policy":[79],"address":[82],"such":[83],"instances.":[84],"On":[85],"example":[87],"small":[90],"quadrotor,":[91],"show":[93,110,146],"that":[94,147],"ground":[96,119],"effect":[97,120],"causes":[98],"an":[101],"otherwise":[102],"functioning":[103],"zero-shot":[104],"framework.":[106],"Our":[107],"experiments":[109],"that,":[111],"even":[112],"explicit":[115],"modelling":[116],"employing":[123],"techniques,":[127],"trained":[129],"policies":[130],"capture":[133],"physical":[135],"nuances":[136],"necessary":[137],"perform":[139],"take-off":[142],"maneuver.":[143],"Contrariwise,":[144],"state-of-the-art":[148],"represent":[153],"feasible,":[155],"reliable":[156],"sample":[158],"efficient":[159],"case.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}