{"id":"https://openalex.org/W2167590754","doi":null,"title":"Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations","display_name":"Scaling Up Approximate Value Iteration with Options: Better Policies with Fewer Iterations","publication_year":2014,"publication_date":"2014-06-21","ids":{"openalex":"https://openalex.org/W2167590754","mag":"2167590754"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.652.4615","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.652.4615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.org/proceedings/papers/v32/mann14.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006380946","display_name":"Timothy Mann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Timothy Mann","raw_affiliation_strings":["Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa, Israel 32000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa, Israel 32000","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647","observed_orcids":["https://orcid.org/0000-0003-4439-7647"]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa, Israel 32000"],"raw_orcid":"https://orcid.org/0000-0003-4439-7647","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Technion - Israel Institute of Technology, Haifa, Israel 32000","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":3.8769,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.93827586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.0006000000284984708,"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/options-framework","display_name":"options framework","score":0.7139999866485596},{"id":"https://openalex.org/keywords/approximate-value-iteration","display_name":"approximate value iteration","score":0.9869999885559082},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9160000085830688},{"id":"https://openalex.org/keywords/continuous-state-spaces","display_name":"continuous state spaces","score":0.9150000214576721},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.953000009059906},{"id":"https://openalex.org/keywords/temporally-extended-actions","display_name":"temporally extended actions","score":0.9089999794960022},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.5189999938011169},{"id":"https://openalex.org/keywords/optimal-replacement","display_name":"optimal replacement","score":0.6759999990463257},{"id":"https://openalex.org/keywords/inventory-management","display_name":"inventory management","score":0.8389999866485596}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.767041027545929},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6845118403434753},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.618375837802887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5790682435035706},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5374003648757935},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5150782465934753},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4895957112312317},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.477815181016922},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4710775911808014},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.42772069573402405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3164517879486084},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.074726402759552},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.06785482168197632},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.652.4615","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.652.4615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://jmlr.org/proceedings/papers/v32/mann14.pdf","raw_type":"text"},{"id":"mag:2167590754","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v32/mann14.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W114364418","https://openalex.org/W1556824961","https://openalex.org/W1600813180","https://openalex.org/W1631187438","https://openalex.org/W2022835057","https://openalex.org/W2109910161","https://openalex.org/W2115502112","https://openalex.org/W2117355432","https://openalex.org/W2130535800","https://openalex.org/W2143435603","https://openalex.org/W2144032829","https://openalex.org/W2156676156","https://openalex.org/W2160808139"],"related_works":["https://openalex.org/W2740174381","https://openalex.org/W1037351197","https://openalex.org/W7095349547","https://openalex.org/W7099686451","https://openalex.org/W7014000748","https://openalex.org/W4387355622","https://openalex.org/W2094964720","https://openalex.org/W2397861913","https://openalex.org/W2105558171","https://openalex.org/W2946258294"],"abstract_inverted_index":{"We":[0,96],"show":[1,97],"how":[2],"options,":[3],"a":[4,17,80],"class":[5],"of":[6,31],"control":[7],"struc-tures":[8],"encompassing":[9],"primitive":[10,55],"and":[11,65,79],"temporally":[12,60],"ex-tended":[13],"actions,":[14],"can":[15,46],"play":[16],"valuable":[18],"role":[19],"in":[20,22,74,94],"plan-ning":[21,52],"MDPs":[23],"with":[24,35,53,113],"continuous":[25],"state-spaces.":[26],"An-alyzing":[27],"the":[28,59,69,86,104],"convergence":[29,49,93,102],"rate":[30],"Approximate":[32],"Value":[33],"Iteration":[34],"options":[36,45,89,99],"reveals":[37],"that":[38,98],"for":[39,88],"pes-simistic":[40],"initial":[41],"value":[42,106],"function":[43],"estimates,":[44],"speed":[47,91],"up":[48,92],"compared":[50],"to":[51,90,103],"only":[54],"actions":[56,62],"even":[57],"when":[58],"extended":[61],"are":[63],"suboptimal":[64],"sparsely":[66],"scattered":[67],"throughout":[68],"state-space.":[70],"Our":[71],"experimental":[72],"results":[73],"an":[75],"optimal":[76],"replace-ment":[77],"task":[78,84],"complex":[81],"inventory":[82],"manage-ment":[83],"demonstrate":[85],"potential":[87],"practice.":[95],"induce":[100],"faster":[101],"op-timal":[105],"function,":[107],"which":[108],"implies":[109],"deriving":[110],"bet-ter":[111],"policies":[112],"fewer":[114],"iterations.":[115],"1.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}