{"id":"https://openalex.org/W7138273080","doi":"https://doi.org/10.1609/aaai.v40i29.39635","title":"Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions","display_name":"Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138273080","doi":"https://doi.org/10.1609/aaai.v40i29.39635"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i29.39635","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39635","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i29.39635","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008151695","display_name":"Rashmeet Kaur Nayyar","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rashmeet Kaur Nayyar","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129663257","display_name":"Naman Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naman Shah","raw_affiliation_strings":["Arizona State University\nBrown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University\nBrown University","institution_ids":["https://openalex.org/I27804330","https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129688097","display_name":"Siddharth Srivastava","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Srivastava","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20688008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"29","first_page":"24522","last_page":"24531"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9516000151634216,"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":0.9516000151634216,"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":0.006200000178068876,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.006000000052154064,"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.843500018119812},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.736299991607666},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6389999985694885},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5925999879837036},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.3808000087738037},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3659000098705292}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.843500018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562000155448914},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.736299991607666},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49559998512268066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3637999892234802},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727999985218048}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i29.39635","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39635","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39635","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i29.39635","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39635","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8124366998672485,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"sequential":[1],"decision-making":[2],"often":[3],"involves":[4],"parameterized":[5,64,94],"action":[6,19,24,38,105],"spaces":[7],"that":[8,62,111],"require":[9],"both,":[10,56],"decisions":[11,16],"regarding":[12],"discrete":[13,50],"actions":[14,53,65,95],"and":[15,40,57,71,104],"about":[17],"continuous":[18,52],"parameters":[20],"governing":[21],"how":[22],"an":[23],"is":[25],"executed.":[26],"Existing":[27],"approaches":[28],"exhibit":[29],"severe":[30],"limitations":[31],"in":[32,121],"this":[33],"setting---planning":[34],"methods":[35,61],"demand":[36],"hand-crafted":[37],"models,":[39],"standard":[41],"reinforcement":[42],"learning":[43],"(RL)":[44],"algorithms":[45,88,110],"are":[46],"designed":[47],"for":[48],"either":[49],"or":[51],"but":[54],"not":[55],"the":[58,75,84,122,126],"few":[59],"RL":[60,87],"handle":[63],"typically":[66],"rely":[67],"on":[68],"domain-specific":[69],"engineering":[70],"fail":[72],"to":[73,89,99,144],"exploit":[74],"latent":[76],"structure":[77],"of":[78,86,125],"these":[79,114],"spaces.":[80],"This":[81],"paper":[82],"extends":[83],"scope":[85],"long-horizon,":[90],"sparse-reward":[91],"settings":[92],"with":[93],"by":[96],"enabling":[97],"agents":[98],"autonomously":[100],"learn":[101],"both":[102],"state":[103],"abstractions":[106,115],"online.":[107],"We":[108],"introduce":[109],"progressively":[112],"refine":[113],"during":[116],"learning,":[117],"increasing":[118],"fine-grained":[119],"detail":[120],"critical":[123],"regions":[124],"state\u2013action":[127],"space":[128],"where":[129],"greater":[130],"resolution":[131],"improves":[132],"performance.":[133],"Across":[134],"several":[135],"continuous-state,":[136],"parameterized-action":[137],"domains,":[138],"our":[139],"abstraction-driven":[140],"approach":[141],"enables":[142],"TD(\u03bb)":[143],"achieve":[145],"markedly":[146],"higher":[147],"sample":[148],"efficiency":[149],"than":[150],"state-of-the-art":[151],"baselines.":[152]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2026-03-18T00:00:00"}