{"id":"https://openalex.org/W2213381658","doi":"https://doi.org/10.1109/iros.2015.7354296","title":"Reinforcement learning vs human programming in tetherball robot games","display_name":"Reinforcement learning vs human programming in tetherball robot games","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2213381658","doi":"https://doi.org/10.1109/iros.2015.7354296","mag":"2213381658"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2015.7354296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5055633714","display_name":"Simone Parisi","orcid":"https://orcid.org/0000-0003-3886-8131"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simone Parisi","raw_affiliation_strings":["Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080021372","display_name":"Hany Abdulsamad","orcid":"https://orcid.org/0000-0001-8683-8784"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hany Abdulsamad","raw_affiliation_strings":["Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086955688","display_name":"Alexandros Paraschos","orcid":"https://orcid.org/0000-0002-3930-4840"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexandros Paraschos","raw_affiliation_strings":["Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047982234","display_name":"Christian Daniel","orcid":"https://orcid.org/0000-0001-7065-5326"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Daniel","raw_affiliation_strings":["Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany","Max Planck Institute for Intelligent Systems, Tubingen, Germany"],"affiliations":[{"raw_affiliation_string":"Autonomous Systems Labs, Technical, University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, Tubingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055633714"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.8897,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83396162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6428","last_page":"6434"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8839470148086548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7229516506195068},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7150088548660278},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.680725634098053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5509310960769653},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48359841108322144},{"id":"https://openalex.org/keywords/motor-skill","display_name":"Motor skill","score":0.4409826397895813},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3873947262763977},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3290271759033203},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.306334912776947},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.110466867685318}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8839470148086548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229516506195068},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7150088548660278},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.680725634098053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509310960769653},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48359841108322144},{"id":"https://openalex.org/C169976356","wikidata":"https://www.wikidata.org/wiki/Q13208902","display_name":"Motor skill","level":2,"score":0.4409826397895813},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3873947262763977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3290271759033203},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.306334912776947},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.110466867685318},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros.2015.7354296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.mpg.de:item_2259773","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002A-1F2A-6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.mpg.de:item_2260923","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-002A-209D-1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1603631609","https://openalex.org/W1988071341","https://openalex.org/W1993300073","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2052668588","https://openalex.org/W2063591749","https://openalex.org/W2111967991","https://openalex.org/W2123967136","https://openalex.org/W2124267516","https://openalex.org/W2130726249","https://openalex.org/W2133761776","https://openalex.org/W2142383762","https://openalex.org/W2167117957","https://openalex.org/W2790374560","https://openalex.org/W6648451707","https://openalex.org/W6653435097","https://openalex.org/W6653548176","https://openalex.org/W6676560026","https://openalex.org/W6678157427","https://openalex.org/W6680987236"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,31,45,54,104,135],"of":[2,22,48,66,113,128],"motor":[3,44,52,72,87],"skills":[4,23],"is":[5,35],"an":[6,110],"important":[7],"challenge":[8],"in":[9,51],"order":[10],"to":[11,17,58,84],"endow":[12],"robots":[13],"with":[14],"the":[15,64,76,86,106,125],"ability":[16],"learn":[18],"a":[19,43,59,140,143],"wide":[20],"range":[21],"and":[24,55,79,89,95,138],"solve":[25],"complex":[26,126],"tasks.":[27],"However,":[28],"comparing":[29],"reinforcement":[30],"against":[32,121,142],"human":[33],"programming":[34],"not":[36],"straightforward.":[37],"In":[38,124],"this":[39],"paper,":[40],"we":[41,131],"create":[42],"framework":[46,88,115],"consisting":[47],"state-of-the-art":[49],"components":[50,99],"skill":[53,103],"compare":[56],"it":[57],"manually":[60],"designed":[61],"program":[62],"on":[63],"task":[65],"robot":[67,117,129],"tetherball.":[68],"We":[69],"use":[70],"dynamical":[71],"primitives":[73],"for":[74,101],"representing":[75],"robot's":[77],"trajectories":[78],"relative":[80],"entropy":[81],"policy":[82],"search":[83],"train":[85],"improve":[90],"its":[91],"behavior":[92],"by":[93],"trial":[94],"error.":[96],"These":[97],"algorithmic":[98],"allow":[100],"high-quality":[102],"while":[105],"experimental":[107],"setup":[108],"enables":[109],"accurate":[111],"evaluation":[112],"our":[114,134],"as":[116],"players":[118],"can":[119],"compete":[120],"each":[122],"other.":[123],"game":[127],"tetherball,":[130],"show":[132],"that":[133],"approach":[136],"outperforms":[137],"wins":[139],"match":[141],"high":[144],"quality":[145],"hand-crafted":[146],"system.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}