{"id":"https://openalex.org/W4403488507","doi":"https://doi.org/10.3233/faia240545","title":"Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments","display_name":"Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488507","doi":"https://doi.org/10.3233/faia240545"},"language":"en","primary_location":{"id":"doi:10.3233/faia240545","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240545","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240545","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240545","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052093184","display_name":"Zoya Volovikova","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zoya Volovikova","raw_affiliation_strings":["AIRI, Moscow, Russia","MIPT, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"MIPT, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089256022","display_name":"Alexey Skrynnik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Skrynnik","raw_affiliation_strings":["AIRI, Moscow, Russia","FRC CSC RAS, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"FRC CSC RAS, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049594901","display_name":"Petr Kuderov","orcid":"https://orcid.org/0000-0001-7055-3426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petr Kuderov","raw_affiliation_strings":["AIRI, Moscow, Russia","MIPT, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"MIPT, Moscow, Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080806360","display_name":"Aleksandr I. Panov","orcid":"https://orcid.org/0000-0002-9747-3837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksandr I. Panov","raw_affiliation_strings":["AIRI, Moscow, Russia","FRC CSC RAS, Moscow, Russia","MIPT, Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"AIRI, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"FRC CSC RAS, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"MIPT, Moscow, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052093184"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3198,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89375542,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10648","display_name":"Virtual Reality Applications and Impacts","score":0.5296000242233276,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10648","display_name":"Virtual Reality Applications and Impacts","score":0.5296000242233276,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.6054261326789856},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6040663719177246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5304027795791626},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46195104718208313},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.311983585357666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1555684506893158},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06925815343856812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6054261326789856},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6040663719177246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5304027795791626},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46195104718208313},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.311983585357666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1555684506893158},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06925815343856812}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240545","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240545","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240545","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240545","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240545","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240545","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403488507.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In":[0,21],"this":[1],"study,":[2],"we":[3,24,52],"address":[4],"the":[5,44,59,68,76,83,103,133],"issue":[6],"of":[7,63,72,105],"enabling":[8],"an":[9],"artificial":[10],"intelligence":[11],"agent":[12],"to":[13,42,118,137],"execute":[14],"complex":[15],"language":[16,61,65,77,84,138],"instructions":[17,28],"within":[18],"virtual":[19],"environments.":[20],"our":[22,106],"framework,":[23],"assume":[25],"that":[26,37,57],"these":[27,50],"involve":[29],"intricate":[30],"linguistic":[31],"structures":[32],"and":[33,121,128],"multiple":[34],"interdependent":[35],"tasks":[36,127],"must":[38],"be":[39],"navigated":[40],"successfully":[41],"achieve":[43],"desired":[45],"outcomes.":[46],"To":[47],"effectively":[48],"manage":[49],"complexities,":[51],"propose":[53],"a":[54,87,96],"hierarchical":[55],"framework":[56],"combines":[58],"deep":[60],"comprehension":[62],"large":[64],"models":[66],"with":[67,130],"adaptive":[69],"action-execution":[70],"capabilities":[71],"reinforcement":[73,98],"learning":[74,99],"agents:":[75],"module":[78],"(based":[79],"on":[80],"LLM)":[81],"translates":[82],"instruction":[85],"into":[86],"high-level":[88],"action":[89],"plan,":[90],"which":[91],"is":[92],"then":[93],"executed":[94],"by":[95],"pre-trained":[97],"agent.We":[100],"have":[101],"demonstrated":[102],"effectiveness":[104],"approach":[107],"in":[108,112,122,132],"two":[109],"different":[110],"environments:":[111],"IGLU,":[113],"where":[114,124],"agents":[115,125],"are":[116],"instructed":[117],"build":[119],"structures,":[120],"Crafter,":[123],"perform":[126],"interact":[129],"objects":[131],"surrounding":[134],"environment":[135],"according":[136],"commands.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
