{"id":"https://openalex.org/W3046387304","doi":"https://doi.org/10.1109/icpr48806.2021.9412421","title":"Low Dimensional State Representation Learning with Reward-shaped Priors","display_name":"Low Dimensional State Representation Learning with Reward-shaped Priors","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3046387304","doi":"https://doi.org/10.1109/icpr48806.2021.9412421","mag":"3046387304"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.utwente.nl/en/publications/98d5bf7e-0b74-4c96-a095-1399e8843a12","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001000324","display_name":"Nicol\u00f2 Botteghi","orcid":"https://orcid.org/0000-0003-3676-3619"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nicolo Botteghi","raw_affiliation_strings":["Robotics and Mechatronics University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046616099","display_name":"Ruben Obbink","orcid":null},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruben Obbink","raw_affiliation_strings":["Robotics and Mechatronics University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038377968","display_name":"Daan Geijs","orcid":"https://orcid.org/0000-0003-3984-1766"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daan Geijs","raw_affiliation_strings":["Robotics and Mechatronics University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046610258","display_name":"Mannes Poel","orcid":"https://orcid.org/0000-0002-3813-9732"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mannes Poel","raw_affiliation_strings":["Datamanagement and Biometrics, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Datamanagement and Biometrics, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056056423","display_name":"Beril S\u0131rma\u00e7ek","orcid":"https://orcid.org/0000-0002-0343-5072"},"institutions":[{"id":"https://openalex.org/I94616838","display_name":"J\u00f6nk\u00f6ping University","ror":"https://ror.org/03t54am93","country_code":"SE","type":"education","lineage":["https://openalex.org/I94616838"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Beril Sirmacek","raw_affiliation_strings":["J\u00f6nk\u00f6ping AI Lab, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J\u00f6nk\u00f6ping AI Lab, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden","institution_ids":["https://openalex.org/I94616838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078725649","display_name":"Christoph Br\u00fcne","orcid":"https://orcid.org/0000-0003-0145-5069"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christoph Brune","raw_affiliation_strings":["Applied Analysis University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Analysis University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012747778","display_name":"Abeje Y. Mersha","orcid":"https://orcid.org/0000-0003-0457-5293"},"institutions":[{"id":"https://openalex.org/I2801398864","display_name":"Saxion","ror":"https://ror.org/005t9n460","country_code":"NL","type":"education","lineage":["https://openalex.org/I2801398864"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Abeje Mersha","raw_affiliation_strings":["Research Group of Mechatronics, Saxion University of Applied Sciences, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Group of Mechatronics, Saxion University of Applied Sciences, Enschede, The Netherlands","institution_ids":["https://openalex.org/I2801398864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047812798","display_name":"Stefano Stramigioli","orcid":"https://orcid.org/0000-0001-8212-7387"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stefano Stramigioli","raw_affiliation_strings":["Robotics and Mechatronics University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and Mechatronics University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2799,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61025036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3736","last_page":"3743"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9909999966621399,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9871000051498413,"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/robotics","display_name":"Robotics","score":0.8037227392196655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7764304280281067},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7762290835380554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7227579355239868},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6082121133804321},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5805988907814026},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5778568983078003},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5716388821601868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5084747076034546},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49270179867744446},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4835948348045349},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.45956164598464966},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4594823122024536},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44643768668174744},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2626131772994995},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11614930629730225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07172304391860962}],"concepts":[{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.8037227392196655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7764304280281067},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7762290835380554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227579355239868},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6082121133804321},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5805988907814026},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5778568983078003},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5716388821601868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5084747076034546},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49270179867744446},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4835948348045349},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.45956164598464966},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4594823122024536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44643768668174744},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2626131772994995},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11614930629730225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07172304391860962},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/98d5bf7e-0b74-4c96-a095-1399e8843a12","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/98d5bf7e-0b74-4c96-a095-1399e8843a12","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Botteghi, N, Obbink, R, Geijs, D, Poel, M, Sirmacek, B, Brune, C, Mersha, A & Stramigioli, S 2021, Low Dimensional State Representation Learning with Reward-shaped Priors. in 2020 25th International Conference on Pattern Recognition (ICPR)., 9412421, pp. 3736-3743, 25th International Conference on Pattern Recognition, ICPR 2020, Virtual, Milan, Italy, 10/01/21. https://doi.org/10.1109/ICPR48806.2021.9412421","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2007.16044","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.16044","pdf_url":"https://arxiv.org/pdf/2007.16044","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/98d5bf7e-0b74-4c96-a095-1399e8843a12","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/98d5bf7e-0b74-4c96-a095-1399e8843a12","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Botteghi, N, Obbink, R, Geijs, D, Poel, M, Sirmacek, B, Brune, C, Mersha, A & Stramigioli, S 2021, Low Dimensional State Representation Learning with Reward-shaped Priors. in 2020 25th International Conference on Pattern Recognition (ICPR)., 9412421, pp. 3736-3743, 25th International Conference on Pattern Recognition, ICPR 2020, Virtual, Milan, Italy, 10/01/21. https://doi.org/10.1109/ICPR48806.2021.9412421","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W199564175","https://openalex.org/W1164749991","https://openalex.org/W1515851193","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W2089468765","https://openalex.org/W2094024286","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2163922914","https://openalex.org/W2187089797","https://openalex.org/W2473208550","https://openalex.org/W2567455162","https://openalex.org/W2619484182","https://openalex.org/W2746553466","https://openalex.org/W2754695199","https://openalex.org/W2787666871","https://openalex.org/W2790924949","https://openalex.org/W2941078345","https://openalex.org/W2951751411","https://openalex.org/W2964112890","https://openalex.org/W2964282857","https://openalex.org/W4214717370","https://openalex.org/W4294226150","https://openalex.org/W4298857966","https://openalex.org/W6635465357"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2930863966","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"has":[2],"been":[3],"able":[4],"to":[5,99],"solve":[6],"many":[7],"complicated":[8],"robotics":[9,56],"tasks":[10,133],"without":[11],"any":[12],"need":[13],"for":[14],"feature":[15],"engineering":[16],"in":[17,134],"an":[18],"end-to-end":[19],"fashion.":[20],"However,":[21],"learning":[22,77,94],"the":[23,28,32,46,50,81,104,107,110,113,116,126],"optimal":[24,117],"policy":[25,118],"directly":[26],"from":[27,54,80,112],"sensory":[29],"inputs,":[30],"i.e":[31],"observations,":[33],"often":[34],"requires":[35],"processing":[36],"and":[37,106,121,138],"storage":[38],"of":[39,43,48,52,103,146],"a":[40,72,78,84,135,141],"huge":[41],"amount":[42],"data.":[44],"In":[45],"context":[47],"robotics,":[49],"cost":[51],"data":[53],"real":[55,142],"hardware":[57],"is":[58,90,119],"usually":[59],"very":[60],"high,":[61],"thus":[62],"solutions":[63],"that":[64,74],"achieve":[65],"high":[66],"sample-efficiency":[67],"are":[68],"needed.":[69],"We":[70,124],"propose":[71],"method":[73,127],"aims":[75],"at":[76],"mapping":[79,89],"observations":[82],"into":[83],"lower-dimensional":[85],"state":[86,114],"space.":[87],"This":[88],"learned":[91],"with":[92],"unsupervised":[93],"using":[95],"loss":[96],"functions":[97],"shaped":[98],"incorporate":[100],"prior":[101],"knowledge":[102],"environment":[105,137],"task.":[108],"Using":[109],"samples":[111],"space,":[115],"quickly":[120],"efficiently":[122],"learned.":[123],"test":[125],"on":[128,140],"several":[129],"mobile":[130],"robot":[131],"navigation":[132],"simulation":[136],"also":[139],"robot.":[143],"A":[144],"video":[145],"our":[147],"experiments":[148],"can":[149],"be":[150],"found":[151],"at:":[152],"https://youtu.be/dgWxmfSv95U.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-03-01T00:00:00"}