{"id":"https://openalex.org/W4416748806","doi":"https://doi.org/10.1109/iros60139.2025.11246276","title":"Addressing Dimensional Scaling in Reinforcement Learning for Symbolic Locomotion Policies through Leveraging Inductive Priors","display_name":"Addressing Dimensional Scaling in Reinforcement Learning for Symbolic Locomotion Policies through Leveraging Inductive Priors","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748806","doi":"https://doi.org/10.1109/iros60139.2025.11246276"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5120523029","display_name":"Rogier Fransen","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rogier Fransen","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044490167","display_name":"Richard Bowden","orcid":"https://orcid.org/0000-0003-3285-8020"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Bowden","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091184063","display_name":"Simon Hadfield","orcid":"https://orcid.org/0000-0001-8637-5054"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Hadfield","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,Guildford,UK,GU2 7XH","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48135276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5221","last_page":"5227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.694100022315979,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.694100022315979,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06790000200271606,"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/T12290","display_name":"Human Motion and Animation","score":0.06040000170469284,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7006999850273132},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6668000221252441},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6341000199317932},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6107000112533569},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5444999933242798},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45750001072883606},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4499000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024000287055969},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7006999850273132},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6668000221252441},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6341000199317932},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6107000112533569},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5444999933242798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534500002861023},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38580000400543213},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":7,"referenced_works":["https://openalex.org/W3093922502","https://openalex.org/W3111294788","https://openalex.org/W3175254947","https://openalex.org/W4383371721","https://openalex.org/W4384824093","https://openalex.org/W4386432078","https://openalex.org/W4402896765"],"related_works":[],"abstract_inverted_index":{"We":[0,32,66,101,121,147],"explore":[1],"symbolic":[2,36,78,129,145],"policy":[3,37],"optimization":[4,38],"for":[5,107],"various":[6],"legged":[7,119],"locomotion":[8,79],"challenges;":[9],"specifically":[10],"walker":[11],"environments":[12],"ranging":[13],"from":[14],"bipedal":[15],"to":[16,41,43,49,52,73,86,136,163],"highly":[17],"redundant":[18],"systems":[19],"with":[20,125,131,143],"128":[21],"legs.":[22],"These":[23],"represent":[24],"a":[25,61,96,105],"broad":[26],"range":[27],"of":[28,77,118],"action":[29,55,90,111],"space":[30,112],"dimensionalities.":[31],"find":[33],"that":[34,123,141,150],"state-of-the-art":[35],"approaches":[39],"struggle":[40],"scale":[42],"these":[44],"higher":[45],"dimensional":[46],"problems,":[47],"due":[48],"the":[50,75,84,89,110,115,137],"need":[51,85],"iterate":[53,87],"over":[54,88],"dimensions,":[56,91],"and":[57,92,168],"their":[58,165],"reliance":[59],"on":[60,152],"neural":[62,98,160],"network":[63,99,161],"anchor":[64],"policy.":[65],"thus":[67],"propose":[68,103],"Fast":[69],"Symbolic":[70],"Policy":[71],"(FSP)":[72],"accelerate":[74],"training":[76,166],"policies.":[80],"This":[81],"approach":[82],"avoids":[83],"does":[93],"not":[94],"require":[95],"pre-trained":[97],"anchor.":[100],"also":[102,156],"Dim-X,":[104],"method":[106],"effectively":[108],"reducing":[109],"dimensionality":[113],"using":[114],"inductive":[116],"priors":[117],"locomotion.":[120],"demonstrate":[122],"FSP":[124],"Dim-X":[126,151],"can":[127,155],"learn":[128],"policies,":[130],"improved":[132],"scaling":[133,170],"performance":[134],"compared":[135],"baselines,":[138],"vastly":[139],"exceeding":[140],"possible":[142],"previous":[144],"techniques.":[146],"further":[148],"show":[149],"its":[153],"own":[154],"be":[157],"integrated":[158],"into":[159],"policies":[162],"shorten":[164],"time":[167],"improve":[169],"performance.":[171]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}