{"id":"https://openalex.org/W7223997474","doi":"https://doi.org/10.48550/arxiv.2610.33817","title":"EnvLunch: The Environment as a Free Lunch for Learning to Interact","display_name":"EnvLunch: The Environment as a Free Lunch for Learning to Interact","publication_year":2026,"publication_date":"2026-10-24","ids":{"openalex":"https://openalex.org/W7223997474","doi":"https://doi.org/10.48550/arxiv.2610.33817"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.33817","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33817","pdf_url":"https://arxiv.org/pdf/2610.33817","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":null,"license_id":null,"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/2610.33817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159808989","display_name":"Wei Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liu, Wei","raw_affiliation_strings":["King's College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159818830","display_name":"Min Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Gao, Min","raw_affiliation_strings":["Chongqing University \u2663 The Alan Turing Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University \u2663 The Alan Turing Institute","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I4210128584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159844268","display_name":"Yali Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5159971158","display_name":"Yulan He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"He, Yulan","raw_affiliation_strings":["King's College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London","institution_ids":["https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5273000001907349,"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":0.5273000001907349,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.07270000129938126,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0478999987244606,"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/language-model-agents","display_name":"language model agents","score":0.8799999952316284},{"id":"https://openalex.org/keywords/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.6499999761581421},{"id":"https://openalex.org/keywords/database-interaction","display_name":"database interaction","score":0.5699999928474426},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738999724388123},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7542999982833862},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7269999980926514},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.6409000158309937},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5806999802589417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4884999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41780000925064087},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.33817","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33817","pdf_url":"https://arxiv.org/pdf/2610.33817","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.33817","doi":"https://doi.org/10.48550/arxiv.2610.33817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.33817","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:2610.33817","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.33817","pdf_url":"https://arxiv.org/pdf/2610.33817","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2577708131","display_name":"Turing AI Fellowship: Event-Centric Framework for Natural Language Understanding","funder_award_id":"EP/V020579/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6382798043","display_name":"Turing AI Fellowship: Event-Centric Framework for Natural Language Understanding","funder_award_id":"EP/V020579/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223997474.pdf","grobid_xml":"https://content.openalex.org/works/W7223997474.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1990391007","https://openalex.org/W2751448157","https://openalex.org/W2973727699","https://openalex.org/W4391631327","https://openalex.org/W4396214235","https://openalex.org/W4403885431","https://openalex.org/W4415601249","https://openalex.org/W4416239856","https://openalex.org/W4416863254","https://openalex.org/W4416959505","https://openalex.org/W4417222331","https://openalex.org/W4417422257","https://openalex.org/W4417515760","https://openalex.org/W7102388436","https://openalex.org/W7117126565","https://openalex.org/W7117716024","https://openalex.org/W7119035063","https://openalex.org/W7125695819","https://openalex.org/W7128399534","https://openalex.org/W7140089314","https://openalex.org/W7155090332","https://openalex.org/W7161261800","https://openalex.org/W7161717673","https://openalex.org/W7208838824"],"related_works":["https://openalex.org/W7160641962","https://openalex.org/W4406733515","https://openalex.org/W4412889815","https://openalex.org/W4415108122","https://openalex.org/W4417100144","https://openalex.org/W7165765930","https://openalex.org/W7214596890","https://openalex.org/W7196954632","https://openalex.org/W7214369949","https://openalex.org/W7165849379"],"abstract_inverted_index":{"For":[0],"agentic":[1,87,213],"data":[2,198],"analysis,":[3],"language-model":[4],"agents":[5],"often":[6],"require":[7,29,61],"a":[8,51,68,107,174,207],"large":[9],"number":[10],"of":[11,57],"annotated":[12,27,150,203],"tasks":[13,28,59,184,204,217],"to":[14,17,97,105,122,145,152],"learn":[15],"how":[16],"interact":[18],"effectively":[19],"with":[20,138],"executable":[21,34],"environments":[22],"(i.e.,":[23],"databases).":[24],"While":[25],"high-quality":[26],"heavy":[30],"manual":[31],"effort,":[32],"an":[33,54,103],"environment":[35,48,168],"already":[36],"provides":[37,206],"rich":[38],"interaction":[39],"structure":[40],"and":[41,101,137,189,205],"verifiable":[42,58],"outcomes.":[43],"In":[44],"this":[45,73,190],"sense,":[46],"the":[47,120,124,141,154,157,167,171,179,186],"itself":[49],"offers":[50],"free":[52],"lunch,":[53],"additional":[55],"set":[56],"that":[60,71,156],"no":[62],"human":[63],"annotation.":[64],"We":[65],"propose":[66],"EnvLunch,":[67],"warm-up":[69,118,191],"stage":[70],"turns":[72],"environmental":[74],"signal":[75],"into":[76],"agent":[77,104],"training":[78,135,164],"without":[79],"human-written":[80],"or":[81],"model-generated":[82],"task":[83,172],"descriptions,":[84],"before":[85],"downstream":[86,134],"reinforcement":[88],"learning.":[89],"EnvLunch":[90,158,200],"samples":[91],"valid":[92],"action":[93],"trajectories,":[94],"executes":[95],"them":[96],"obtain":[98],"final":[99,114],"observations,":[100],"trains":[102],"recover":[106],"functionally":[108],"equivalent":[109],"trajectory":[110],"given":[111],"only":[112],"its":[113,162,182],"observation.":[115],"This":[116],"label-free":[117],"enables":[119],"model":[121,159,180],"outperform":[123],"baseline":[125,142],"by":[126],"over":[127,185],"9":[128],"points":[129],"on":[130,195],"average":[131],"across":[132],"all":[133],"budgets,":[136],"few":[139],"labels,":[140],"needs":[143],"8":[144],"32":[146],"times":[147],"as":[148],"many":[149],"examples":[151],"match":[153],"accuracy":[155],"reaches":[160],"at":[161],"smallest":[163],"budget.":[165],"Letting":[166],"alone":[169],"define":[170],"yields":[173],"larger":[175],"gain":[176],"than":[177],"having":[178],"write":[181],"own":[183],"same":[187],"environments,":[188],"also":[192],"improves":[193],"fine-tuning":[194,212],"benchmarks":[196],"beyond":[197],"analysis.":[199],"therefore":[201],"saves":[202],"better":[208],"starting":[209],"point":[210],"for":[211],"models":[214],"when":[215],"such":[216],"are":[218],"limited.":[219]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-28T00:00:00"}