{"id":"https://openalex.org/W7156325498","doi":"https://doi.org/10.48550/arxiv.2604.22081","title":"Insect-inspired modular architectures as inductive biases for reinforcement learning","display_name":"Insect-inspired modular architectures as inductive biases for reinforcement learning","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7156325498","doi":"https://doi.org/10.48550/arxiv.2604.22081"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.22081","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.22081","pdf_url":"https://arxiv.org/pdf/2604.22081","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.22081","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072240246","display_name":"Anne Staples","orcid":"https://orcid.org/0000-0003-4823-8184","observed_orcids":["https://orcid.org/0000-0003-4823-8184"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Staples, Anne E.","raw_affiliation_strings":["Department of Mechanical Engineering , Virginia Tech , Blacksburg , Virginia 24061 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering , Virginia Tech , Blacksburg , Virginia 24061 , USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072240246"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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"}},{"id":"https://openalex.org/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","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/distributed-control","display_name":"distributed control","score":0.8259999752044678},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.9760000109672546},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7889999747276306},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.640999972820282},{"id":"https://openalex.org/keywords/navigation","display_name":"navigation","score":0.3199999928474426},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"obstacle avoidance","score":0.7519999742507935},{"id":"https://openalex.org/keywords/predator-evasion","display_name":"predator escape","score":0.9340000152587891},{"id":"https://openalex.org/keywords/food-seeking","display_name":"food seeking","score":0.8690000176429749},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.8149999976158142},{"id":"https://openalex.org/keywords/control-allocation","display_name":"control allocation","score":0.31299999356269836}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7343000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026000142097473},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4399999976158142},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.430400013923645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C2781121602","wikidata":"https://www.wikidata.org/wiki/Q3504403","display_name":"Modular neural network","level":4,"score":0.3474000096321106},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C81988521","wikidata":"https://www.wikidata.org/wiki/Q676838","display_name":"Control unit","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C137813230","wikidata":"https://www.wikidata.org/wiki/Q2996165","display_name":"Motor control","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C2776937971","wikidata":"https://www.wikidata.org/wiki/Q4384217","display_name":"Heading (navigation)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C2983526489","wikidata":"https://www.wikidata.org/wiki/Q133500","display_name":"Associative learning","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.22081","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.22081","pdf_url":"https://arxiv.org/pdf/2604.22081","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.2604.22081","doi":"https://doi.org/10.48550/arxiv.2604.22081","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22081","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:2604.22081","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.22081","pdf_url":"https://arxiv.org/pdf/2604.22081","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7156325498.pdf","grobid_xml":"https://content.openalex.org/works/W7156325498.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3041686449","https://openalex.org/W2992675430","https://openalex.org/W3094221113","https://openalex.org/W7098143642","https://openalex.org/W6999003141","https://openalex.org/W7095690691","https://openalex.org/W3202797049","https://openalex.org/W2900747781","https://openalex.org/W3164709982","https://openalex.org/W2735028559"],"abstract_inverted_index":{"Most":[0],"reinforcement-learning":[1],"(RL)":[2],"controllers":[3],"used":[4],"in":[5,36],"continuous":[6],"control":[7,29,68,190,197],"are":[8,12,26,31],"architecturally":[9],"centralized:":[10],"observations":[11],"compressed":[13],"into":[14,69],"a":[15,52,88,103,118,152,161,201],"single":[16,53],"latent":[17],"state":[18],"from":[19],"which":[20],"both":[21],"value":[22,174],"estimates":[23],"and":[24,43,83,114,158,176],"actions":[25],"produced.":[27],"Biological":[28],"systems":[30],"often":[32],"organized":[33],"differently.":[34],"Insects,":[35],"particular,":[37],"coordinate":[38],"navigation,":[39],"heading":[40,75],"stabilization,":[41],"memory,":[42,79],"context-dependent":[44],"action":[45],"selection":[46],"through":[47],"distributed":[48,196],"circuits":[49],"rather":[50],"than":[51],"monolithic":[54],"controller.":[55],"Motivated":[56],"by":[57],"this":[58],"contrast,":[59],"we":[60],"study":[61],"an":[62],"RL":[63,206],"policy":[64,133,168],"architecture":[65],"that":[66,92,107,195],"decomposes":[67],"interacting":[70],"modules":[71],"for":[72,128,151,160,205],"sensory":[73],"encoding,":[74],"representation,":[76],"sparse":[77],"associative":[78],"recurrent":[80,155],"command":[81],"generation,":[82],"local":[84],"motor":[85,94],"control,":[86],"with":[87,123,144],"learned":[89],"arbitration":[90],"mechanism":[91],"allocates":[93],"authority":[95],"across":[96],"modules.":[97],"The":[98,166],"model":[99],"is":[100],"evaluated":[101],"on":[102],"two-dimensional":[104],"navigation":[105],"task":[106],"require":[108],"simultaneous":[109],"food":[110],"seeking,":[111],"obstacle":[112],"avoidance,":[113],"predator":[115],"escape.":[116],"In":[117],"six-seed":[119],"predator-navigation":[120],"experiment":[121],"trained":[122],"Proximal":[124],"Policy":[125],"Optimization":[126],"(PPO)":[127],"75":[129],"updates,":[130],"the":[131,135,141,171],"modular":[132,167],"achieves":[134],"strongest":[136],"final":[137,145,173],"mean":[138],"performance":[139],"among":[140],"tested":[142],"controllers,":[143],"episodic":[146],"return":[147],"$-2798.8\\pm964.4$":[148],"versus":[149],"$-3778.0\\pm628.1$":[150],"centralized":[153,162],"gated":[154],"unit":[156],"(GRU)":[157],"$-4727.5\\pm772.5$":[159],"multilayer":[163],"perceptron":[164],"(MLP).":[165],"also":[169],"attains":[170],"lowest":[172],"loss":[175],"stable":[177],"PPO":[178],"optimization":[179],"statistics":[180],"while":[181],"driving":[182],"module-assignment":[183],"entropy":[184],"to":[185],"$0.0457\\pm0.0244$,":[186],"indicating":[187],"highly":[188],"selective":[189],"allocation.":[191],"These":[192],"results":[193],"suggest":[194],"can":[198],"serve":[199],"as":[200],"useful":[202],"inductive":[203],"bias":[204],"problems":[207],"involving":[208],"dynamically":[209],"competing":[210],"behavioral":[211],"objectives.":[212]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-04-28T00:00:00"}