{"id":"https://openalex.org/W4415314459","doi":"https://doi.org/10.48550/arxiv.2510.06277","title":"Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning","display_name":"Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-06","ids":{"openalex":"https://openalex.org/W4415314459","doi":"https://doi.org/10.48550/arxiv.2510.06277"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.06277","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.06277","pdf_url":"https://arxiv.org/pdf/2510.06277","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.06277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099881289","display_name":"Fahim Shahriar","orcid":"https://orcid.org/0009-0000-2091-6495","observed_orcids":["https://orcid.org/0009-0000-2091-6495","https://orcid.org/0000-0001-8885-5203"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4405260365","display_name":"Alberta Machine Intelligence Institute","ror":"https://ror.org/03msd8560","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4405260365"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shahriar, Fahim","raw_affiliation_strings":["Alberta Machine Intelligence Institute (Amii)","University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alberta Machine Intelligence Institute (Amii)","institution_ids":["https://openalex.org/I4405260365"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130813696","display_name":"Cheryl Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wang, Cheryl","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Azimi, Alireza","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4405260365","display_name":"Alberta Machine Intelligence Institute","ror":"https://ror.org/03msd8560","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4405260365"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Azimi, Alireza","raw_affiliation_strings":["Alberta Machine Intelligence Institute (Amii)","University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alberta Machine Intelligence Institute (Amii)","institution_ids":["https://openalex.org/I4405260365"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103860806","display_name":"Gautham Vasan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4405260365","display_name":"Alberta Machine Intelligence Institute","ror":"https://ror.org/03msd8560","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4405260365"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vasan, Gautham","raw_affiliation_strings":["Alberta Machine Intelligence Institute (Amii)","University of Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alberta Machine Intelligence Institute (Amii)","institution_ids":["https://openalex.org/I4405260365"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681764","display_name":"Hany Hamed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamed, Hany","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Naik, Abhishek","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Naik, Abhishek","raw_affiliation_strings":["National Research Council Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council Canada","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102815213","display_name":"A. Rupam Mahmood","orcid":"https://orcid.org/0000-0002-2640-1844","observed_orcids":["https://orcid.org/0000-0002-2640-1844"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahmood, A. Rupam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033365772","display_name":"Colin Bellinger","orcid":"https://orcid.org/0000-0002-3567-7834","observed_orcids":["https://orcid.org/0000-0002-3567-7834"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bellinger, Colin","raw_affiliation_strings":["University of Ottawa","Vector Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ottawa","institution_ids":["https://openalex.org/I153718931"]},{"raw_affiliation_string":"Vector Institute","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.002899999963119626,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/goal-conditioned-reinforcement-learning","display_name":"goal-conditioned reinforcement learning","score":0.9959999918937683},{"id":"https://openalex.org/keywords/robotic-arm-manipulation","display_name":"robotic arm manipulation","score":0.6620000004768372},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.9350000023841858},{"id":"https://openalex.org/keywords/generalization-to-novel-objects","display_name":"novel object generalization","score":0.6589999794960022},{"id":"https://openalex.org/keywords/vision-based-robot-control","display_name":"vision-based robot control","score":0.43700000643730164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694000005722046},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7573999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.722599983215332},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6352999806404114},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5723999738693237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5392000079154968},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37770000100135803},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.06277","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.06277","pdf_url":"https://arxiv.org/pdf/2510.06277","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.06277","doi":"https://doi.org/10.48550/arxiv.2510.06277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.06277","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.06277","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.06277","pdf_url":"https://arxiv.org/pdf/2510.06277","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415314459.pdf","grobid_xml":"https://content.openalex.org/works/W4415314459.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2789008106","https://openalex.org/W2978730776","https://openalex.org/W4285601030","https://openalex.org/W4323066621","https://openalex.org/W7163889864"],"related_works":["https://openalex.org/W7106029637","https://openalex.org/W4414943832","https://openalex.org/W4206684559","https://openalex.org/W7215038920","https://openalex.org/W4381233049","https://openalex.org/W4283753019","https://openalex.org/W4403535342","https://openalex.org/W4383108444","https://openalex.org/W4402660054","https://openalex.org/W4393905143"],"abstract_inverted_index":{"Goal-conditioned":[0],"reinforcement":[1],"learning":[2,150,157],"(GCRL)":[3],"offers":[4],"a":[5,58,82,131],"unified":[6],"way":[7],"to":[8,40,118],"pursue":[9],"diverse":[10],"tasks,":[11],"yet":[12],"most":[13],"existing":[14],"methods":[15],"rely":[16],"on":[17,163],"state-":[18],"or":[19,34,46,92,98],"position-based":[20],"goal":[21,42,61,79,83,110],"representations":[22],"that":[23,63],"are":[24],"unavailable":[25],"in":[26,31,128,135,151],"real-world":[27,174],"robotics.":[28],"Robots":[29],"operating":[30],"warehouses,":[32],"agriculture,":[33],"laboratory":[35],"environments":[36],"rarely":[37],"have":[38],"access":[39],"privileged":[41,109],"states,":[43,111],"object":[44,90],"positions,":[45],"future":[47],"observations,":[48],"limiting":[49],"the":[50,104,168],"practicality":[51],"of":[52,170],"current":[53],"GCRL":[54],"approaches.":[55],"We":[56,154],"propose":[57],"dynamic":[59],"mask-based":[60],"representation":[62],"provides":[64],"simple,":[65],"object-agnostic":[66],"visual":[67],"cues":[68],"for":[69,173],"vision-based":[70],"navigation":[71],"and":[72,115,125,139,144,148,160],"manipulation.":[73],"At":[74],"each":[75],"timestep,":[76],"an":[77],"image-based":[78],"detector":[80],"produces":[81],"mask":[84],"using":[85],"standard":[86],"image":[87],"processing,":[88],"task-specific":[89],"recognizers,":[91],"pretrained":[93],"detectors":[94],"such":[95],"as":[96],"Detic":[97],"Grounding":[99],"DINO.":[100],"These":[101],"masks":[102],"specify":[103],"spatial":[105],"target":[106],"without":[107],"requiring":[108],"enabling":[112],"broad":[113],"applicability":[114],"strong":[116],"generalization":[117],"unseen":[119],"objects.":[120],"Our":[121,177],"method":[122],"improves":[123],"stability":[124],"sample":[126],"efficiency":[127],"GCRL,":[129],"achieving":[130],"99%":[132],"success":[133],"rate":[134],"reaching":[136],"both":[137,164],"training":[138],"novel":[140],"objects":[141],"with":[142],"Franka":[143],"UR10e":[145],"robotic":[146,165],"arms":[147],"faster":[149],"simulated":[152],"navigation.":[153],"further":[155],"demonstrate":[156],"from":[158],"scratch":[159],"sim-to-real":[161],"transfer":[162],"arms,":[166],"highlighting":[167],"effectiveness":[169],"our":[171],"approach":[172],"RL":[175],"tasks.":[176],"code":[178],"is":[179],"available":[180],"at":[181],"https://github.com/fahimfss/GCRL.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-18T00:00:00"}