{"id":"https://openalex.org/W3216082637","doi":"https://doi.org/10.1109/lra.2021.3129833","title":"Learning Robotic Manipulation Tasks via Task Progress Based Gaussian Reward and Loss Adjusted Exploration","display_name":"Learning Robotic Manipulation Tasks via Task Progress Based Gaussian Reward and Loss Adjusted Exploration","publication_year":2021,"publication_date":"2021-11-23","ids":{"openalex":"https://openalex.org/W3216082637","doi":"https://doi.org/10.1109/lra.2021.3129833","mag":"3216082637"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3129833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3129833","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5031476331","display_name":"Sulabh Kumra","orcid":"https://orcid.org/0000-0003-2792-0969"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sulabh Kumra","raw_affiliation_strings":["OSARO Inc., San Francisco, CA, USA","Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-2792-0969","affiliations":[{"raw_affiliation_string":"OSARO Inc., San Francisco, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038392758","display_name":"Shirin Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shirin Joshi","raw_affiliation_strings":["Siemens Corporation, Corporate Technology, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporation, Corporate Technology, Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023942737","display_name":"Ferat Sahin","orcid":"https://orcid.org/0000-0002-9813-7165"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ferat Sahin","raw_affiliation_strings":["Multi-Agent Bio-Robotics Laboratory, Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-9813-7165","affiliations":[{"raw_affiliation_string":"Multi-Agent Bio-Robotics Laboratory, Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3534,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80973884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"7","issue":"1","first_page":"534","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9747999906539917,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9021000266075134,"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/computer-science","display_name":"Computer science","score":0.74156653881073},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7387427091598511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6648620963096619},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6498763561248779},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5402289628982544},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5375885963439941},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5185061693191528},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45022812485694885},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4275904595851898},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09218406677246094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74156653881073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7387427091598511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6648620963096619},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6498763561248779},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5402289628982544},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5375885963439941},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5185061693191528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45022812485694885},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4275904595851898},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09218406677246094},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3129833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3129833","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1968069998","https://openalex.org/W1999156278","https://openalex.org/W2036637075","https://openalex.org/W2167489871","https://openalex.org/W2201912979","https://openalex.org/W2300618187","https://openalex.org/W2890646997","https://openalex.org/W2962736495","https://openalex.org/W2962746398","https://openalex.org/W2962793652","https://openalex.org/W2963326767","https://openalex.org/W2963411833","https://openalex.org/W2963713397","https://openalex.org/W2991276239","https://openalex.org/W3004003541","https://openalex.org/W3006398608","https://openalex.org/W3008535267","https://openalex.org/W3022674252","https://openalex.org/W3026627579","https://openalex.org/W3091340437","https://openalex.org/W3091471537","https://openalex.org/W3091677803","https://openalex.org/W3092037789","https://openalex.org/W3101103779","https://openalex.org/W3130885760","https://openalex.org/W3131005319","https://openalex.org/W3132971170","https://openalex.org/W3204744691","https://openalex.org/W3205304947","https://openalex.org/W3207647944","https://openalex.org/W6746713385","https://openalex.org/W6748523217","https://openalex.org/W6785308759"],"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/W2912415823","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"Multi-step":[0],"manipulation":[1,56,82,160],"tasks":[2,15,161,201],"in":[3,162,181],"unstructured":[4],"environments":[5],"are":[6,197],"extremely":[7],"challenging":[8,157],"for":[9,200],"a":[10,47,60,71,87,123],"robot":[11],"to":[12,29,53,75,104,137,154],"learn.":[13],"Such":[14],"interlace":[16],"high-level":[17],"reasoning":[18,36],"that":[19,25,37,95,102,129,170,193],"consists":[20],"of":[21,119,141,148,183],"the":[22,77,97,111,117,133,138,146,174],"expected":[23],"states":[24],"can":[26],"be":[27],"attained":[28],"achieve":[30],"an":[31],"overall":[32,112],"task":[33,113],"and":[34,80,108,165,177,186,195],"low-level":[35],"decides":[38],"what":[39],"actions":[40,101,131],"will":[41],"yield":[42],"these":[43],"states.":[44],"We":[45,58,85,144],"propose":[46],"model-free":[48],"deep":[49],"reinforcement":[50],"learning":[51],"method":[52,172],"learn":[54,76,155],"multi-step":[55,158],"tasks.":[57],"introduce":[59,122],"Robotic":[61],"Manipulation":[62],"Network":[63],"(RoManNet)":[64],"<sup":[65],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[66],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[67],",":[68],"which":[69],"is":[70],"vision-based":[72],"model":[73],"architecture,":[74],"action-value":[78],"functions":[79],"predict":[81],"action":[83,134,187],"candidates.":[84],"define":[86],"Task":[88],"Progress":[89],"based":[90,99],"Gaussian":[91],"(TPG)":[92],"reward":[93,98],"function":[94],"computes":[96],"on":[100],"lead":[103],"successful":[105],"motion":[106],"primitives":[107],"progress":[109],"towards":[110],"goal.":[114],"To":[115],"balance":[116],"ratio":[118],"exploration/exploitation,":[120],"we":[121],"Loss":[124],"Adjusted":[125],"Exploration":[126],"(LAE)":[127],"policy":[128],"determines":[130],"from":[132],"candidates":[135],"according":[136],"Boltzmann":[139],"distribution":[140],"loss":[142],"estimates.":[143],"demonstrate":[145],"effectiveness":[147],"our":[149,171],"approach":[150],"by":[151],"training":[152],"RoManNet":[153],"several":[156],"robotic":[159],"both":[163],"simulation":[164],"real-world.":[166],"Experimental":[167],"results":[168],"show":[169,192],"outperforms":[173],"existing":[175],"methods":[176],"achieves":[178],"state-of-the-art":[179],"performance":[180],"terms":[182],"success":[184],"rate":[185],"efficiency.":[188],"The":[189],"ablation":[190],"studies":[191],"TPG":[194],"LAE":[196],"especially":[198],"beneficial":[199],"like":[202],"multiple":[203],"block":[204],"stacking.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}