{"id":"https://openalex.org/W4414432258","doi":"https://doi.org/10.1109/case58245.2025.11164095","title":"Physical State Exploration for Reinforcement Learning from Scratch","display_name":"Physical State Exploration for Reinforcement Learning from Scratch","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414432258","doi":"https://doi.org/10.1109/case58245.2025.11164095"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11164095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11164095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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/A5013330580","display_name":"Allison Pinosky","orcid":"https://orcid.org/0000-0002-3095-8856"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH","US"],"is_corresponding":false,"raw_author_name":"Allison Pinosky","raw_affiliation_strings":["Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA","institution_ids":["https://openalex.org/I111979921","https://openalex.org/I4210100400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043752929","display_name":"Thomas A. Berrueta","orcid":"https://orcid.org/0000-0002-3781-0934"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH","US"],"is_corresponding":false,"raw_author_name":"Thomas A. Berrueta","raw_affiliation_strings":["Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA","institution_ids":["https://openalex.org/I111979921","https://openalex.org/I4210100400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045084510","display_name":"Olivia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH","US"],"is_corresponding":false,"raw_author_name":"Olivia Li","raw_affiliation_strings":["Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA","institution_ids":["https://openalex.org/I111979921","https://openalex.org/I4210100400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067725461","display_name":"Todd D. Murphey","orcid":"https://orcid.org/0000-0003-2262-8176"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210100400","display_name":"Northwestern University","ror":"https://ror.org/00m6w7z96","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210100400"]}],"countries":["PH","US"],"is_corresponding":false,"raw_author_name":"Todd D. Murphey","raw_affiliation_strings":["Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Department of Mechanical Engineering,Chicago,IL,USA","institution_ids":["https://openalex.org/I111979921","https://openalex.org/I4210100400"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1715","last_page":"1721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9190000295639038,"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":0.9190000295639038,"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/scratch","display_name":"Scratch","score":0.8027999997138977},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7591000199317932},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6728000044822693},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.638700008392334},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5268999934196472},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5055999755859375}],"concepts":[{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.8027999997138977},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7591000199317932},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6728000044822693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643999814987183},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.638700008392334},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5102999806404114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.30059999227523804},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11164095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11164095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1974461875","https://openalex.org/W2054115913","https://openalex.org/W2056370235","https://openalex.org/W2132351269","https://openalex.org/W2145339207","https://openalex.org/W2146262966","https://openalex.org/W2158782408","https://openalex.org/W2737347195","https://openalex.org/W2738778707","https://openalex.org/W2767050701","https://openalex.org/W2804400276","https://openalex.org/W2963411833","https://openalex.org/W2963523627","https://openalex.org/W2964137828","https://openalex.org/W2968585391","https://openalex.org/W3088310808","https://openalex.org/W3091886887","https://openalex.org/W3126321819","https://openalex.org/W3207033168","https://openalex.org/W4285129493","https://openalex.org/W4312596169","https://openalex.org/W4312900875","https://openalex.org/W4390968535","https://openalex.org/W4396583645","https://openalex.org/W4401416330","https://openalex.org/W4402353773","https://openalex.org/W4403676845","https://openalex.org/W4403677072","https://openalex.org/W4405785373"],"related_works":[],"abstract_inverted_index":{"Although":[0],"reinforcement":[1],"learning":[2,89,110,119],"(RL)":[3],"algorithms":[4,61,96,109],"have":[5],"demonstrated":[6],"impressive":[7],"capabilities":[8],"in":[9,103,144],"simulation,":[10],"their":[11],"transition":[12],"into":[13],"the":[14,50,112,116,125,137],"real-world":[15,25,47],"often":[16],"reveals":[17],"a":[18,76,121],"performance":[19,48],"gap.":[20],"A":[21],"key":[22],"challenge":[23],"of":[24,127,139],"deployment":[26],"is":[27,84],"ensuring":[28],"robustness":[29],"to":[30,55,86,99,118,131,142],"complex":[31],"or":[32],"unmodeled":[33],"physical":[34,63],"phenomena,":[35],"such":[36],"as":[37],"anisotropic":[38],"friction":[39],"during":[40],"locomotion.":[41],"This":[42,82],"discrepancy":[43],"between":[44],"simulated":[45,122],"and":[46,58,114,150],"underscores":[49],"need":[51],"for":[52,62,79],"hardware":[53,77,146],"benchmarks":[54],"rigorously":[56],"evaluate":[57],"improve":[59],"RL":[60,80],"deployment.":[64],"In":[65],"this":[66],"work,":[67],"we":[68],"present":[69],"NoodleBot\u2014a":[70],"low-cost,":[71],"untethered":[72],"three-link":[73],"swimmer":[74],"robot\u2014as":[75],"benchmark":[78,83],"algorithms.":[81],"intended":[85],"complement":[87],"embodied":[88],"approaches,":[90],"where":[91],"simulations":[92],"provide":[93],"confidence":[94],"that":[95],"are":[97,152],"able":[98],"learn":[100,143],"from":[101],"scratch":[102],"challenging":[104],"environments.":[105],"We":[106,134],"demonstrate":[107],"three":[108],"on":[111],"platform":[113],"compare":[115],"results":[117],"with":[120],"swimmer,":[123],"highlighting":[124],"importance":[126],"effective":[128],"state":[129],"exploration":[130],"agent":[132],"performance.":[133],"also":[135],"show":[136],"ability":[138],"one":[140],"algorithm":[141],"single-shot":[145],"deployments.":[147],"Design,":[148],"firmware,":[149],"software":[151],"available":[153],"open":[154],"source":[155],"at":[156],"https://github.com/MurpheyLab/NoodleBot.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}