{"id":"https://openalex.org/W2567455162","doi":"https://doi.org/10.1109/iros.2016.7759578","title":"Stable reinforcement learning with autoencoders for tactile and visual data","display_name":"Stable reinforcement learning with autoencoders for tactile and visual data","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2567455162","doi":"https://doi.org/10.1109/iros.2016.7759578","mag":"2567455162"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2016.7759578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2016.7759578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5057277609","display_name":"Herke van Hoof","orcid":"https://orcid.org/0000-0002-1583-3692"},"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":"Herke van Hoof","raw_affiliation_strings":["IAS institute, TU, Darmstadt"],"affiliations":[{"raw_affiliation_string":"IAS institute, TU, Darmstadt","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014597367","display_name":"Nutan Chen","orcid":"https://orcid.org/0000-0001-7571-0742"},"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":"Nutan Chen","raw_affiliation_strings":["Faculty for Informatics, TU, M\u00fcnchen"],"affiliations":[{"raw_affiliation_string":"Faculty for Informatics, TU, M\u00fcnchen","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035705687","display_name":"Maximilian Karl","orcid":"https://orcid.org/0000-0001-8959-368X"},"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":"Maximilian Karl","raw_affiliation_strings":["Faculty for Informatics, TU, M\u00fcnchen"],"affiliations":[{"raw_affiliation_string":"Faculty for Informatics, TU, M\u00fcnchen","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022626150","display_name":"Patrick van der Smagt","orcid":"https://orcid.org/0000-0003-4418-4916"},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick van der Smagt","raw_affiliation_strings":["Fortiss, TUM Associate Institute"],"affiliations":[{"raw_affiliation_string":"Fortiss, TUM Associate Institute","institution_ids":["https://openalex.org/I4210134795"]}]},{"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":["IAS institute, TU, Darmstadt","Max Planck Institute for Intelligent Systems"],"affiliations":[{"raw_affiliation_string":"IAS institute, TU, Darmstadt","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057277609"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":17.297,"has_fulltext":false,"cited_by_count":141,"citation_normalized_percentile":{"value":0.9912427,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3928","last_page":"3934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T10581","display_name":"Neural dynamics and brain function","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.9789000153541565,"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":0.8590744733810425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7817113399505615},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6685318350791931},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6375076174736023},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.627865195274353},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6250836849212646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6041601300239563},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.43523073196411133},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.41005754470825195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4080413281917572},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.364189088344574},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33768606185913086},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07001715898513794}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8590744733810425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817113399505615},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6685318350791931},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6375076174736023},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.627865195274353},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6250836849212646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6041601300239563},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.43523073196411133},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.41005754470825195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4080413281917572},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.364189088344574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33768606185913086},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07001715898513794},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2016.7759578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2016.7759578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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":49,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W199564175","https://openalex.org/W314779054","https://openalex.org/W834081922","https://openalex.org/W1499669280","https://openalex.org/W1539716820","https://openalex.org/W1564755532","https://openalex.org/W1771410628","https://openalex.org/W1957496711","https://openalex.org/W1959608418","https://openalex.org/W1968962398","https://openalex.org/W1977655452","https://openalex.org/W1979709633","https://openalex.org/W2006273250","https://openalex.org/W2025768430","https://openalex.org/W2038794597","https://openalex.org/W2046023599","https://openalex.org/W2069361969","https://openalex.org/W2070678636","https://openalex.org/W2072128103","https://openalex.org/W2100235553","https://openalex.org/W2107726111","https://openalex.org/W2108579172","https://openalex.org/W2112645080","https://openalex.org/W2144902422","https://openalex.org/W2145339207","https://openalex.org/W2146662771","https://openalex.org/W2172158418","https://openalex.org/W2172425052","https://openalex.org/W2173248099","https://openalex.org/W2176035349","https://openalex.org/W2179072710","https://openalex.org/W2210408922","https://openalex.org/W2213467466","https://openalex.org/W2443711627","https://openalex.org/W2962986780","https://openalex.org/W2963430173","https://openalex.org/W2963634205","https://openalex.org/W2963864421","https://openalex.org/W2964161785","https://openalex.org/W4231109964","https://openalex.org/W6623316541","https://openalex.org/W6633472939","https://openalex.org/W6638018090","https://openalex.org/W6640963894","https://openalex.org/W6681302627","https://openalex.org/W6684921986","https://openalex.org/W6685152286","https://openalex.org/W6685755111"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W3203657119","https://openalex.org/W4286952720"],"abstract_inverted_index":{"For":[0],"many":[1],"tasks,":[2,47],"tactile":[3,31,125],"or":[4,9,53],"visual":[5,115],"feedback":[6,19],"is":[7,22,78],"helpful":[8],"even":[10],"crucial.":[11],"However,":[12],"designing":[13],"controllers":[14],"that":[15,90],"take":[16],"such":[17,46,65,75],"high-dimensional":[18],"into":[20],"account":[21],"non-trivial.":[23],"Therefore,":[24,83],"robots":[25],"should":[26],"be":[27,81],"able":[28],"to":[29,59,80],"learn":[30,92],"skills":[32],"through":[33],"trial":[34],"and":[35],"error":[36],"by":[37],"using":[38,103],"reinforcement":[39,87],"learning":[40,88],"algorithms.":[41],"The":[42],"input":[43],"domain":[44],"for":[45],"however,":[48],"might":[49],"include":[50],"strongly":[51],"correlated":[52],"non-relevant":[54],"dimensions,":[55],"making":[56],"it":[57],"hard":[58],"specify":[60],"a":[61,76,86,111,123],"suitable":[62],"metric":[63,77],"on":[64,110,122],"domains.":[66],"Auto-encoders":[67],"specialize":[68],"in":[69,95],"finding":[70],"compact":[71],"representations,":[72],"where":[73],"defining":[74],"likely":[79],"easier.":[82],"we":[84,118],"propose":[85],"algorithm":[89],"can":[91],"non-linear":[93],"policies":[94],"continuous":[96],"state":[97],"spaces,":[98],"which":[99],"leverages":[100],"representations":[101],"learned":[102],"auto-encoders.":[104],"We":[105],"first":[106],"evaluate":[107],"this":[108],"method":[109],"simulated":[112],"toy-task":[113],"with":[114],"input.":[116],"Then,":[117],"validate":[119],"our":[120],"approach":[121],"real-robot":[124],"stabilization":[126],"task.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}
