{"id":"https://openalex.org/W3205321526","doi":"https://doi.org/10.1109/icra48506.2021.9561103","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","display_name":"Generalization in Reinforcement Learning by Soft Data Augmentation","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3205321526","doi":"https://doi.org/10.1109/icra48506.2021.9561103","mag":"3205321526"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5086722753","display_name":"Nicklas Hansen","orcid":"https://orcid.org/0000-0001-9897-4003"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK","US"],"is_corresponding":true,"raw_author_name":"Nicklas Hansen","raw_affiliation_strings":["University of California,San Diego,CA,USA","University of California, San Diego, CA, USA","Technical University of Denmark, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego,CA,USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Technical University of Denmark, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424275","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0003-3150-778X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["University of California,San Diego,CA,USA","University of California, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego,CA,USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086722753"],"corresponding_institution_ids":["https://openalex.org/I36258959","https://openalex.org/I96673099"],"apc_list":null,"apc_paid":null,"fwci":10.3545,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.98565975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13611","last_page":"13617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8424816131591797},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8405478000640869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753414511680603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5891989469528198},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.566260039806366},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.560575008392334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5497352480888367},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5332866311073303},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4773963987827301},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45835888385772705},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4574962258338928},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10870873928070068},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08326154947280884}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8424816131591797},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8405478000640869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753414511680603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5891989469528198},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.566260039806366},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.560575008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5497352480888367},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5332866311073303},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4773963987827301},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45835888385772705},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4574962258338928},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10870873928070068},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08326154947280884},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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":97,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W343636949","https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W1836465849","https://openalex.org/W2155007355","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2605102758","https://openalex.org/W2732026016","https://openalex.org/W2766614170","https://openalex.org/W2767050701","https://openalex.org/W2781585732","https://openalex.org/W2798991696","https://openalex.org/W2808849637","https://openalex.org/W2810785043","https://openalex.org/W2823112946","https://openalex.org/W2842511635","https://openalex.org/W2898436992","https://openalex.org/W2903181768","https://openalex.org/W2904246096","https://openalex.org/W2904338767","https://openalex.org/W2949117887","https://openalex.org/W2949517790","https://openalex.org/W2950197980","https://openalex.org/W2962884155","https://openalex.org/W2962887844","https://openalex.org/W2963420272","https://openalex.org/W2963864421","https://openalex.org/W2963906246","https://openalex.org/W2963913081","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2964198579","https://openalex.org/W2964342357","https://openalex.org/W2977481643","https://openalex.org/W2979395451","https://openalex.org/W2980550111","https://openalex.org/W2994066474","https://openalex.org/W2994073215","https://openalex.org/W2995652426","https://openalex.org/W2996283175","https://openalex.org/W3005680577","https://openalex.org/W3021708257","https://openalex.org/W3023640063","https://openalex.org/W3026092005","https://openalex.org/W3034781633","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036670859","https://openalex.org/W3041404693","https://openalex.org/W3041890730","https://openalex.org/W3046419021","https://openalex.org/W3085605093","https://openalex.org/W3090943552","https://openalex.org/W3101442004","https://openalex.org/W3106428938","https://openalex.org/W3108655343","https://openalex.org/W3115293622","https://openalex.org/W4287667696","https://openalex.org/W4287811291","https://openalex.org/W4297789758","https://openalex.org/W4297808394","https://openalex.org/W4298857966","https://openalex.org/W6631190155","https://openalex.org/W6637967152","https://openalex.org/W6638667902","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6704369950","https://openalex.org/W6740934225","https://openalex.org/W6745744936","https://openalex.org/W6747387971","https://openalex.org/W6752601656","https://openalex.org/W6753060773","https://openalex.org/W6753243525","https://openalex.org/W6754725917","https://openalex.org/W6756103505","https://openalex.org/W6756840741","https://openalex.org/W6757337448","https://openalex.org/W6757592117","https://openalex.org/W6763442200","https://openalex.org/W6768511085","https://openalex.org/W6769201093","https://openalex.org/W6769729221","https://openalex.org/W6771570156","https://openalex.org/W6771750343","https://openalex.org/W6774314701","https://openalex.org/W6775634482","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6777179611","https://openalex.org/W6779326418","https://openalex.org/W6780189587","https://openalex.org/W6781203905","https://openalex.org/W6781494318","https://openalex.org/W6782858274"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W4390516098"],"abstract_inverted_index":{"Extensive":[0],"efforts":[1],"have":[2],"been":[3],"made":[4],"to":[5,79,123],"improve":[6],"the":[7,75,81,93],"generalization":[8],"ability":[9],"of":[10,25,47,87],"Reinforcement":[11],"Learning":[12],"(RL)":[13],"methods":[14],"via":[15],"domain":[16],"randomization":[17],"and":[18,35,43,89,119,129],"data":[19],"augmentation.":[20],"However,":[21],"as":[22,112,114],"more":[23],"factors":[24],"variation":[26],"are":[27,103],"introduced":[28],"during":[29],"training,":[30],"optimization":[31,95],"becomes":[32],"increasingly":[33],"challenging,":[34],"empirically":[36],"may":[37],"result":[38],"in":[39,131],"lower":[40],"sample":[41,126],"efficiency":[42],"unstable":[44],"training.":[45],"Instead":[46],"learning":[48],"policies":[49],"directly":[50],"from":[51,65,108],"augmented":[52,88],"data,":[53,91],"we":[54,120],"propose":[55],"SOft":[56],"Data":[57],"Augmentation":[58],"(SODA),":[59],"a":[60,71,115],"method":[61],"that":[62,77],"decouples":[63],"augmentation":[64],"policy":[66],"learning.":[67],"Specifically,":[68],"SODA":[69,122],"imposes":[70],"soft":[72],"constraint":[73],"on":[74,105],"encoder":[76],"aims":[78],"maximize":[80],"mutual":[82],"information":[83],"between":[84],"latent":[85],"representations":[86],"non-augmented":[90,99],"while":[92],"RL":[94,136],"process":[96],"uses":[97],"strictly":[98],"data.":[100],"Empirical":[101],"evaluations":[102],"performed":[104],"diverse":[106],"tasks":[107],"DeepMind":[109],"Control":[110],"suite":[111],"well":[113],"robotic":[116],"manipulation":[117],"task,":[118],"find":[121],"significantly":[124],"advance":[125],"efficiency,":[127],"generalization,":[128],"stability":[130],"training":[132],"over":[133],"state-of-the-art":[134],"vision-based":[135],"methods.<sup>1</sup>":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":6}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}