{"id":"https://openalex.org/W7147336522","doi":"https://doi.org/10.48550/arxiv.2603.28955","title":"Enhancing Policy Learning with World-Action Model","display_name":"Enhancing Policy Learning with World-Action Model","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147336522","doi":"https://doi.org/10.48550/arxiv.2603.28955"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.28955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28955","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.28955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110953473","display_name":"Yuci Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Han, Yuci","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132598267","display_name":"Alper Yilmaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilmaz, Alper","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110953473"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.40459999442100525,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.40459999442100525,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.20659999549388885,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03830000013113022,"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/policy-learning","display_name":"Policy learning","score":0.6901000142097473},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5338000059127808},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3499999940395355},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3384999930858612},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3366999924182892}],"concepts":[{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6901000142097473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5971999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.28955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28955","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.28955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.28955","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[{"score":0.5445245504379272,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,19,50,73,96,102,134],"World-Action":[4],"Model":[5],"(WAM),":[6],"an":[7,36],"action-regularized":[8],"world":[9,27,86,98],"model":[10,87],"that":[11,21,42],"jointly":[12],"reasons":[13],"over":[14,118],"future":[15],"visual":[16],"observations":[17],"and":[18,120],"actions":[20,44],"drive":[22],"state":[23,47],"transitions.":[24],"Unlike":[25],"conventional":[26],"models":[28],"trained":[29],"solely":[30],"via":[31,82],"image":[32],"prediction,":[33],"WAM":[34,63,108,126],"incorporates":[35],"inverse":[37],"dynamics":[38],"objective":[39],"into":[40],"DreamerV2":[41,119],"predicts":[43],"from":[45,72,114],"latent":[46],"transitions,":[48],"encouraging":[49],"learned":[51],"representations":[52],"to":[53,116],"capture":[54],"action-relevant":[55],"structure":[56],"critical":[57],"for":[58,133],"downstream":[59],"control.":[60],"We":[61,76],"evaluate":[62],"on":[64,85],"enhancing":[65],"policy":[66,81,103],"learning":[67],"across":[68],"eight":[69],"manipulation":[70],"tasks":[71,138],"CALVIN":[74],"benchmark.":[75],"first":[77],"pretrain":[78],"a":[79],"diffusion":[80],"behavioral":[83,111],"cloning":[84,112],"latents,":[88],"then":[89],"refine":[90],"it":[91],"with":[92,136],"model-based":[93],"PPO":[94,124],"inside":[95],"frozen":[97],"model.":[99],"Without":[100],"modifying":[101],"architecture":[104],"or":[105],"training":[106,144],"procedure,":[107],"improves":[109],"average":[110,129],"success":[113,130],"59.4%":[115],"71.2%":[117],"DiWA":[121],"baselines.":[122],"After":[123],"fine-tuning,":[125],"achieves":[127],"92.8%":[128],"versus":[131],"79.8%":[132],"baseline,":[135],"two":[137],"reaching":[139],"100%,":[140],"using":[141],"8.7x":[142],"fewer":[143],"steps.":[145]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}