{"id":"https://openalex.org/W7214137018","doi":null,"title":"Interpretable Meta-Reinforcement Learning : Explicit Task Inference and Epistemic Exploration in Procedural Environments","display_name":"Interpretable Meta-Reinforcement Learning : Explicit Task Inference and Epistemic Exploration in Procedural Environments","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7214137018"},"language":"en","primary_location":{"id":"pmh:oai:ddd.uab.cat:336316","doi":null,"is_oa":true,"landing_page_url":"https://ddd.uab.cat/record/336316","pdf_url":"https://ddd.uab.cat/pub/tfg/2025/336316/interpretable_meta-reinforcement_learning.pdf","source":{"id":"https://openalex.org/S4306400380","display_name":"Dip\u00f2sit Digital de Documents de la UAB (Universitat Aut\u00f2noma de Barcelona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I123044942","host_organization_name":"Universitat Aut\u00f2noma de Barcelona","host_organization_lineage":["https://openalex.org/I123044942"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Treball final de grau"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ddd.uab.cat/pub/tfg/2025/336316/interpretable_meta-reinforcement_learning.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152542226","display_name":"Pol Puig Puy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puig Puy, Pol","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121321196","display_name":"Universitat Aut\u00f2noma de Barcelona. Escola d'Enginyeria","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Universitat Aut\u00f2noma de Barcelona. Escola d'Enginyeria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.9990000128746033,"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":0.9990000128746033,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.000699999975040555,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"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/meta-reinforcement-learning","display_name":"meta-reinforcement learning","score":0.9279999732971191},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.8889999985694885},{"id":"https://openalex.org/keywords/task-inference","display_name":"task inference","score":0.6700000166893005},{"id":"https://openalex.org/keywords/belief-entropy","display_name":"belief entropy","score":0.6150000095367432},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.6359999775886536},{"id":"https://openalex.org/keywords/rule-mining","display_name":"rule discovery","score":0.4429999887943268},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575000286102295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366000175476074},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5360999703407288},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5063999891281128},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C5065155","wikidata":"https://www.wikidata.org/wiki/Q1185775","display_name":"Frame problem","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ddd.uab.cat:336316","doi":null,"is_oa":true,"landing_page_url":"https://ddd.uab.cat/record/336316","pdf_url":"https://ddd.uab.cat/pub/tfg/2025/336316/interpretable_meta-reinforcement_learning.pdf","source":{"id":"https://openalex.org/S4306400380","display_name":"Dip\u00f2sit Digital de Documents de la UAB (Universitat Aut\u00f2noma de Barcelona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I123044942","host_organization_name":"Universitat Aut\u00f2noma de Barcelona","host_organization_lineage":["https://openalex.org/I123044942"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Treball final de grau"}],"best_oa_location":{"id":"pmh:oai:ddd.uab.cat:336316","doi":null,"is_oa":true,"landing_page_url":"https://ddd.uab.cat/record/336316","pdf_url":"https://ddd.uab.cat/pub/tfg/2025/336316/interpretable_meta-reinforcement_learning.pdf","source":{"id":"https://openalex.org/S4306400380","display_name":"Dip\u00f2sit Digital de Documents de la UAB (Universitat Aut\u00f2noma de Barcelona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I123044942","host_organization_name":"Universitat Aut\u00f2noma de Barcelona","host_organization_lineage":["https://openalex.org/I123044942"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Treball final de grau"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326826","display_name":"Universitat Aut\u00f2noma de Barcelona","ror":"https://ror.org/052g8jq94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214137018.pdf","grobid_xml":"https://content.openalex.org/works/W7214137018.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2578206533","https://openalex.org/W2736601468","https://openalex.org/W2945020056","https://openalex.org/W4309183395","https://openalex.org/W4382319558","https://openalex.org/W4389500798"],"related_works":["https://openalex.org/W3126935522","https://openalex.org/W4401555987","https://openalex.org/W6884764601","https://openalex.org/W3157186377","https://openalex.org/W4415798287","https://openalex.org/W2745260329","https://openalex.org/W4400581349","https://openalex.org/W2945020056","https://openalex.org/W4382449358","https://openalex.org/W4394947052"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2,20],"(DRL)":[3],"struggles":[4],"to":[5,45,156,180],"generalise":[6],"across":[7],"varying":[8],"environments,":[9],"often":[10],"memorising":[11],"trajectories":[12],"rather":[13],"than":[14],"inferring":[15],"underlying":[16],"causal":[17],"rules.":[18],"Meta-Reinforcement":[19],"(Meta-RL)":[21],"addresses":[22],"this":[23],"by":[24],"treating":[25],"adaptation":[26],"as":[27,36],"an":[28,57,207],"optimisation":[29],"problem,":[30],"yet":[31],"standard":[32],"recurrent":[33,62],"agents":[34],"act":[35],"opaque":[37],"black":[38],"boxes.":[39],"This":[40,54],"opacity":[41],"makes":[42],"it":[43,151],"difficult":[44],"distinguish":[46],"Bayes-adaptive":[47],"epistemic":[48,146,169],"exploration":[49,155,170],"from":[50,153,211],"blind":[51],"statistical":[52],"heuristics.":[53],"thesis":[55],"introduces":[56],"interpretable":[58],"Meta-RL":[59],"architecture:":[60],"a":[61,70,77,200],"Proximal":[63],"Policy":[64],"Optimisation":[65],"(PPO)":[66],"agent":[67,94,144],"augmented":[68],"with":[69],"supervised":[71],"''Scientist":[72],"Head''.":[73],"Operating":[74],"within":[75,183],"''RuleSalad'',":[76],"novel":[78],"and":[79,89,97,102,124,165,194,206],"computationally":[80],"lightweight":[81],"Gym-MiniGrid":[82],"benchmark":[83],"featuring":[84],"progressive":[85],"levels":[86],"of":[87,105,168],"parametric":[88],"non-parametric":[90],"procedural":[91],"randomisation,":[92],"the":[93,99,106,119,140,143,184],"explicitly":[95],"infers":[96],"classifies":[98],"hidden":[100],"rules":[101],"reward":[103],"objectives":[104],"Partially":[107],"Observable":[108],"Markov":[109],"Decision":[110],"Process":[111],"(POMDP)":[112],"at":[113,171],"each":[114],"time":[115],"step.":[116],"By":[117],"decoding":[118],"agent's":[120],"internal":[121],"belief":[122,177],"state":[123],"measuring":[125],"its":[126],"Shannon":[127],"entropy,":[128],"we":[129,192],"map":[130],"mathematical":[131],"uncertainty":[132],"directly":[133],"onto":[134],"human-understandable":[135],"metrics.":[136],"Our":[137],"framework":[138],"visualises":[139],"exact":[141],"moment":[142],"resolves":[145],"uncertainty,":[147],"empirically":[148,160],"showing":[149],"when":[150],"shifts":[152],"hypothesis-driven":[154],"optimal":[157],"exploitation.":[158],"We":[159],"evaluate":[161],"seven":[162],"experimental":[163],"conditions":[164],"find":[166],"evidence":[167],"lower":[172],"complexity":[173],"levels,":[174],"where":[175],"within-episode":[176],"entropy":[178],"collapses":[179],"\u22480.55":[181],"nats":[182],"first":[185],"calibration":[186],"steps.":[187],"At":[188],"higher":[189],"combinatorial":[190],"limits,":[191],"identify":[193],"diagnose":[195],"two":[196],"structural":[197],"architectural":[198],"boundaries:":[199],"grounding":[201],"problem":[202],"in":[203],"semantic":[204],"decoding,":[205],"exploration-inference":[208],"gap,":[209],"arising":[210],"single-episode":[212],"amnesiac":[213],"resets":[214],"under":[215],"destructive":[216],"probing.":[217]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-24T00:00:00"}