{"id":"https://openalex.org/W7225336607","doi":"https://doi.org/10.20944/preprints202611.0897.v1","title":"LRLS-v1.1: A Specification and Reference Simulation for Dual-Agent Exploration\u2013Exploitation Under Hard Constraints","display_name":"LRLS-v1.1: A Specification and Reference Simulation for Dual-Agent Exploration\u2013Exploitation Under Hard Constraints","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225336607","doi":"https://doi.org/10.20944/preprints202611.0897.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0897.v1","doi":"https://doi.org/10.20944/preprints202611.0897.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0897.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0897.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157817600","display_name":"Jason Sang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jason Sang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5157817600"],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7196999788284302,"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":0.7196999788284302,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.2328999936580658,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.02239999920129776,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.9559999704360962},{"id":"https://openalex.org/keywords/constrained-optimization","display_name":"constrained optimization","score":0.9020000100135803},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.656000018119812},{"id":"https://openalex.org/keywords/hard-constraints","display_name":"hard constraints","score":0.6399999856948853},{"id":"https://openalex.org/keywords/reference-simulation","display_name":"reference simulation","score":0.6389999985694885},{"id":"https://openalex.org/keywords/heterogeneous-robot-fleets","display_name":"heterogeneous robot fleets","score":0.7900000214576721},{"id":"https://openalex.org/keywords/geometric-embedding","display_name":"geometric embedding","score":0.5920000076293945},{"id":"https://openalex.org/keywords/consensus-voting","display_name":"consensus voting","score":0.996999979019165},{"id":"https://openalex.org/keywords/safety-layer","display_name":"safety layer","score":0.6050000190734863},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.4970000088214874},{"id":"https://openalex.org/keywords/state-decomposition","display_name":"state decomposition","score":0.4819999933242798},{"id":"https://openalex.org/keywords/action-primitives","display_name":"action primitives","score":0.5090000033378601},{"id":"https://openalex.org/keywords/training-pipeline","display_name":"training pipeline","score":0.6549999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027000188827515},{"id":"https://openalex.org/C62989814","wikidata":"https://www.wikidata.org/wiki/Q854648","display_name":"Gossip","level":2,"score":0.5539000034332275},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C116253237","wikidata":"https://www.wikidata.org/wiki/Q1437424","display_name":"Formal specification","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C84651959","wikidata":"https://www.wikidata.org/wiki/Q17052506","display_name":"System requirements specification","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C117222624","wikidata":"https://www.wikidata.org/wiki/Q7575010","display_name":"Specification","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.20944/preprints202611.0897.v1","doi":"https://doi.org/10.20944/preprints202611.0897.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0897.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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":"posted-content"},{"id":"doi:10.5281/zenodo.23984054","doi":"https://doi.org/10.5281/zenodo.23984054","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23984054","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23984055","doi":"https://doi.org/10.5281/zenodo.23984055","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23984055","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.20944/preprints202611.0897.v1","doi":"https://doi.org/10.20944/preprints202611.0897.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0897.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"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":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2229557793","https://openalex.org/W7015067478","https://openalex.org/W3037023372","https://openalex.org/W4406297534","https://openalex.org/W7167077070","https://openalex.org/W2565260993","https://openalex.org/W2243284550","https://openalex.org/W7214228360","https://openalex.org/W7211903356","https://openalex.org/W6907637849"],"abstract_inverted_index":{"We":[0,110],"present":[1],"LRLS":[2],"(Lobster":[3],"RL":[4],"Specification),":[5],"a":[6,26,38,58,78,94,98,107,120,125,145,171,174,178,215,226],"formal":[7],"specification":[8,70,141,172],"for":[9],"constrained":[10],"optimisation":[11],"in":[12],"which":[13,115],"the":[14,72,117,140,210],"classical":[15],"exploration--exploitation":[16],"trade-off":[17],"is":[18,170,207],"role-separated":[19],"into":[20,46],"two":[21],"heterogeneous":[22,121],"agent":[23],"populations":[24],"plus":[25],"scheduler.":[27],"A":[28],"high-entropy":[29],"crayfish":[30],"population":[31,43,61],"generates":[32],"coarse":[33],"candidate":[34],"habitats":[35],"(\"mud":[36],"caves\");":[37],"low-entropy,":[39],"constraint-aware":[40],"Boston":[41],"lobster":[42],"promotes":[44],"candidates":[45],"verified":[47],"feasible":[48],"solutions":[49],"(\"reef":[50],"gaps\")":[51],"via":[52],"local":[53],"refinement":[54],"and":[55,65,106,134,160,173,192],"constraint":[56],"projection;":[57],"scheduler":[59,218],"allocates":[60],"budgets,":[62],"dispatches":[63],"tasks":[64],"triggers":[66],"global":[67],"resampling.":[68],"The":[69,205],"fixes":[71],"state":[73],"decomposition,":[74],"six":[75],"action":[76],"primitives,":[77],"single":[79],"reward":[80,156],"structure":[81],"\\(r":[82],"=":[83],"r_{\\mathrm{obj}}":[84],"-":[85,91],"\\lambda_v":[86],"C_v":[87],"+":[88],"\\lambda_e":[89],"\\mathcal{H}":[90],"\\lambda_m":[92],"C_m\\),":[93],"shared":[95],"memory-pool":[96],"schema,":[97],"four-stage":[99],"training":[100],"pipeline,":[101],"seven":[102],"mandatory":[103],"reported":[104,197],"metrics":[105],"safety":[108],"layer.":[109],"additionally":[111],"describe":[112],"v1.1":[113],"RoboZero,":[114],"maps":[116],"agents":[118],"onto":[119],"robot":[122],"fleet":[123],"with":[124],"geometric":[126],"embedding":[127],"space,":[128],"gossip-synchronised":[129],"memory,":[130],"multi-robot":[131],"consensus":[132],"voting":[133],"zero-shot":[135],"transfer":[136],"routes.":[137],"To":[138],"make":[139],"executable,":[142],"we":[143],"release":[144],"dependency-free":[146],"deterministic":[147],"reference":[148,175],"simulation":[149],"(single":[150],"HTML":[151],"file,":[152],"1100":[153],"ticks,":[154],"\\(22\\times22\\)":[155],"terrain,":[157],"12":[158],"agents)":[159],"report":[161],"illustrative":[162],"single-run":[163],"behaviour":[164],"across":[165],"four":[166],"difficulty":[167],"settings.":[168],"This":[169],"implementation,":[176],"not":[177],"claim":[179],"of":[180],"algorithmic":[181],"superiority.":[182],"No":[183],"learned":[184,216],"policy,":[185],"no":[186,189,193],"multi-seed":[187],"statistics,":[188],"baseline":[190],"comparison":[191],"physical-robot":[194],"experiment":[195],"are":[196],"here;":[198],"Section":[199],"6":[200],"states":[201],"these":[202],"limitations":[203],"explicitly.":[204],"aim":[206],"to":[208],"give":[209],"central":[211],"hypothesis":[212],"---":[213,225],"that":[214,230],"switching":[217],"outperforms":[219],"fixed":[220],"temperature":[221],"or":[222],"entropy":[223],"annealing":[224],"precise,":[227],"reproducible":[228],"target":[229],"can":[231],"subsequently":[232],"be":[233],"falsified.":[234]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-06T00:00:00"}