Prior-dependent analysis of posterior sampling reinforcement learning with function approximation Article Swipe
Yingru Li
,
Zhi‐Quan Luo
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.11175
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.11175
This work advances randomized exploration in reinforcement learning (RL) with function approximation modeled by linear mixture MDPs. We establish the first prior-dependent Bayesian regret bound for RL with function approximation; and refine the Bayesian regret analysis for posterior sampling reinforcement learning (PSRL), presenting an upper bound of ${\mathcal{O}}(d\sqrt{H^3 T \log T})$, where $d$ represents the dimensionality of the transition kernel, $H$ the planning horizon, and $T$ the total number of interactions. This signifies a methodological enhancement by optimizing the $\mathcal{O}(\sqrt{\log T})$ factor over the previous benchmark (Osband and Van Roy, 2014) specified to linear mixture MDPs. Our approach, leveraging a value-targeted model learning perspective, introduces a decoupling argument and a variance reduction technique, moving beyond traditional analyses reliant on confidence sets and concentration inequalities to formalize Bayesian regret bounds more effectively.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2403.11175
- https://arxiv.org/pdf/2403.11175
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392972286
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392972286Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2403.11175Digital Object Identifier
- Title
-
Prior-dependent analysis of posterior sampling reinforcement learning with function approximationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-17Full publication date if available
- Authors
-
Yingru Li, Zhi‐Quan LuoList of authors in order
- Landing page
-
https://arxiv.org/abs/2403.11175Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2403.11175Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2403.11175Direct OA link when available
- Concepts
-
Reinforcement learning, Sampling (signal processing), Reinforcement, Function (biology), Statistics, Computer science, Artificial intelligence, Mathematics, Machine learning, Psychology, Biology, Social psychology, Computer vision, Evolutionary biology, Filter (signal processing)Top concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4392972286 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2403.11175 |
| ids.doi | https://doi.org/10.48550/arxiv.2403.11175 |
| ids.openalex | https://openalex.org/W4392972286 |
| fwci | |
| type | preprint |
| title | Prior-dependent analysis of posterior sampling reinforcement learning with function approximation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11601 |
| topics[0].field.id | https://openalex.org/fields/28 |
| topics[0].field.display_name | Neuroscience |
| topics[0].score | 0.9496999979019165 |
| topics[0].domain.id | https://openalex.org/domains/1 |
| topics[0].domain.display_name | Life Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2804 |
| topics[0].subfield.display_name | Cellular and Molecular Neuroscience |
| topics[0].display_name | Neuroscience and Neural Engineering |
| topics[1].id | https://openalex.org/T10784 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9289000034332275 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2204 |
| topics[1].subfield.display_name | Biomedical Engineering |
| topics[1].display_name | Muscle activation and electromyography studies |
| topics[2].id | https://openalex.org/T11749 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9133999943733215 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2207 |
| topics[2].subfield.display_name | Control and Systems Engineering |
| topics[2].display_name | Iterative Learning Control Systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C97541855 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7554221153259277 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q830687 |
| concepts[0].display_name | Reinforcement learning |
| concepts[1].id | https://openalex.org/C140779682 |
| concepts[1].level | 3 |
| concepts[1].score | 0.5825191140174866 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q210868 |
| concepts[1].display_name | Sampling (signal processing) |
| concepts[2].id | https://openalex.org/C67203356 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5771763324737549 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1321905 |
| concepts[2].display_name | Reinforcement |
| concepts[3].id | https://openalex.org/C14036430 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5259419083595276 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3736076 |
| concepts[3].display_name | Function (biology) |
| concepts[4].id | https://openalex.org/C105795698 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4326429069042206 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[4].display_name | Statistics |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.40954315662384033 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.36995840072631836 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C33923547 |
| concepts[7].level | 0 |
| concepts[7].score | 0.3555441200733185 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[7].display_name | Mathematics |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.32507389783859253 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C15744967 |
| concepts[9].level | 0 |
| concepts[9].score | 0.28486600518226624 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[9].display_name | Psychology |
| concepts[10].id | https://openalex.org/C86803240 |
| concepts[10].level | 0 |
| concepts[10].score | 0.10145127773284912 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[10].display_name | Biology |
| concepts[11].id | https://openalex.org/C77805123 |
| concepts[11].level | 1 |
| concepts[11].score | 0.10087364912033081 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q161272 |
| concepts[11].display_name | Social psychology |
| concepts[12].id | https://openalex.org/C31972630 |
| concepts[12].level | 1 |
| concepts[12].score | 0.07697227597236633 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[12].display_name | Computer vision |
| concepts[13].id | https://openalex.org/C78458016 |
| concepts[13].level | 1 |
| concepts[13].score | 0.05718427896499634 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q840400 |
| concepts[13].display_name | Evolutionary biology |
| concepts[14].id | https://openalex.org/C106131492 |
| concepts[14].level | 2 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q3072260 |
| concepts[14].display_name | Filter (signal processing) |
| keywords[0].id | https://openalex.org/keywords/reinforcement-learning |
| keywords[0].score | 0.7554221153259277 |
| keywords[0].display_name | Reinforcement learning |
| keywords[1].id | https://openalex.org/keywords/sampling |
| keywords[1].score | 0.5825191140174866 |
| keywords[1].display_name | Sampling (signal processing) |
| keywords[2].id | https://openalex.org/keywords/reinforcement |
| keywords[2].score | 0.5771763324737549 |
| keywords[2].display_name | Reinforcement |
| keywords[3].id | https://openalex.org/keywords/function |
| keywords[3].score | 0.5259419083595276 |
| keywords[3].display_name | Function (biology) |
| keywords[4].id | https://openalex.org/keywords/statistics |
| keywords[4].score | 0.4326429069042206 |
| keywords[4].display_name | Statistics |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.40954315662384033 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.36995840072631836 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/mathematics |
| keywords[7].score | 0.3555441200733185 |
| keywords[7].display_name | Mathematics |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.32507389783859253 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/psychology |
| keywords[9].score | 0.28486600518226624 |
| keywords[9].display_name | Psychology |
| keywords[10].id | https://openalex.org/keywords/biology |
| keywords[10].score | 0.10145127773284912 |
| keywords[10].display_name | Biology |
| keywords[11].id | https://openalex.org/keywords/social-psychology |
| keywords[11].score | 0.10087364912033081 |
| keywords[11].display_name | Social psychology |
| keywords[12].id | https://openalex.org/keywords/computer-vision |
| keywords[12].score | 0.07697227597236633 |
| keywords[12].display_name | Computer vision |
| keywords[13].id | https://openalex.org/keywords/evolutionary-biology |
| keywords[13].score | 0.05718427896499634 |
| keywords[13].display_name | Evolutionary biology |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2403.11175 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2403.11175 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2403.11175 |
| locations[1].id | doi:10.48550/arxiv.2403.11175 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2403.11175 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5024774792 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3258-9230 |
| authorships[0].author.display_name | Yingru Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Li, Yingru |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101766226 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3995-914X |
| authorships[1].author.display_name | Zhi‐Quan Luo |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Luo, Zhi-Quan |
| authorships[1].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2403.11175 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-03-20T00:00:00 |
| display_name | Prior-dependent analysis of posterior sampling reinforcement learning with function approximation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11601 |
| primary_topic.field.id | https://openalex.org/fields/28 |
| primary_topic.field.display_name | Neuroscience |
| primary_topic.score | 0.9496999979019165 |
| primary_topic.domain.id | https://openalex.org/domains/1 |
| primary_topic.domain.display_name | Life Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2804 |
| primary_topic.subfield.display_name | Cellular and Molecular Neuroscience |
| primary_topic.display_name | Neuroscience and Neural Engineering |
| related_works | https://openalex.org/W2920061524, https://openalex.org/W4310083477, https://openalex.org/W2328553770, https://openalex.org/W1977959518, https://openalex.org/W2038908348, https://openalex.org/W2107890255, https://openalex.org/W2106552856, https://openalex.org/W2145821588, https://openalex.org/W2086122291, https://openalex.org/W1987513656 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2403.11175 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2403.11175 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2403.11175 |
| primary_location.id | pmh:oai:arXiv.org:2403.11175 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2403.11175 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2403.11175 |
| publication_date | 2024-03-17 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.T | 48 |
| abstract_inverted_index.a | 73, 99, 105, 109 |
| abstract_inverted_index.RL | 26 |
| abstract_inverted_index.We | 17 |
| abstract_inverted_index.an | 43 |
| abstract_inverted_index.by | 13, 76 |
| abstract_inverted_index.in | 5 |
| abstract_inverted_index.of | 46, 56, 69 |
| abstract_inverted_index.on | 118 |
| abstract_inverted_index.to | 92, 124 |
| abstract_inverted_index.$H$ | 60 |
| abstract_inverted_index.$T$ | 65 |
| abstract_inverted_index.$d$ | 52 |
| abstract_inverted_index.Our | 96 |
| abstract_inverted_index.Van | 88 |
| abstract_inverted_index.and | 30, 64, 87, 108, 121 |
| abstract_inverted_index.for | 25, 36 |
| abstract_inverted_index.the | 19, 32, 54, 57, 61, 66, 78, 83 |
| abstract_inverted_index.(RL) | 8 |
| abstract_inverted_index.Roy, | 89 |
| abstract_inverted_index.This | 0, 71 |
| abstract_inverted_index.T})$ | 80 |
| abstract_inverted_index.\log | 49 |
| abstract_inverted_index.more | 129 |
| abstract_inverted_index.over | 82 |
| abstract_inverted_index.sets | 120 |
| abstract_inverted_index.with | 9, 27 |
| abstract_inverted_index.work | 1 |
| abstract_inverted_index.2014) | 90 |
| abstract_inverted_index.MDPs. | 16, 95 |
| abstract_inverted_index.T})$, | 50 |
| abstract_inverted_index.bound | 24, 45 |
| abstract_inverted_index.first | 20 |
| abstract_inverted_index.model | 101 |
| abstract_inverted_index.total | 67 |
| abstract_inverted_index.upper | 44 |
| abstract_inverted_index.where | 51 |
| abstract_inverted_index.beyond | 114 |
| abstract_inverted_index.bounds | 128 |
| abstract_inverted_index.factor | 81 |
| abstract_inverted_index.linear | 14, 93 |
| abstract_inverted_index.moving | 113 |
| abstract_inverted_index.number | 68 |
| abstract_inverted_index.refine | 31 |
| abstract_inverted_index.regret | 23, 34, 127 |
| abstract_inverted_index.(Osband | 86 |
| abstract_inverted_index.(PSRL), | 41 |
| abstract_inverted_index.kernel, | 59 |
| abstract_inverted_index.mixture | 15, 94 |
| abstract_inverted_index.modeled | 12 |
| abstract_inverted_index.reliant | 117 |
| abstract_inverted_index.Bayesian | 22, 33, 126 |
| abstract_inverted_index.advances | 2 |
| abstract_inverted_index.analyses | 116 |
| abstract_inverted_index.analysis | 35 |
| abstract_inverted_index.argument | 107 |
| abstract_inverted_index.function | 10, 28 |
| abstract_inverted_index.horizon, | 63 |
| abstract_inverted_index.learning | 7, 40, 102 |
| abstract_inverted_index.planning | 62 |
| abstract_inverted_index.previous | 84 |
| abstract_inverted_index.sampling | 38 |
| abstract_inverted_index.variance | 110 |
| abstract_inverted_index.approach, | 97 |
| abstract_inverted_index.benchmark | 85 |
| abstract_inverted_index.establish | 18 |
| abstract_inverted_index.formalize | 125 |
| abstract_inverted_index.posterior | 37 |
| abstract_inverted_index.reduction | 111 |
| abstract_inverted_index.signifies | 72 |
| abstract_inverted_index.specified | 91 |
| abstract_inverted_index.confidence | 119 |
| abstract_inverted_index.decoupling | 106 |
| abstract_inverted_index.introduces | 104 |
| abstract_inverted_index.leveraging | 98 |
| abstract_inverted_index.optimizing | 77 |
| abstract_inverted_index.presenting | 42 |
| abstract_inverted_index.randomized | 3 |
| abstract_inverted_index.represents | 53 |
| abstract_inverted_index.technique, | 112 |
| abstract_inverted_index.transition | 58 |
| abstract_inverted_index.enhancement | 75 |
| abstract_inverted_index.exploration | 4 |
| abstract_inverted_index.traditional | 115 |
| abstract_inverted_index.effectively. | 130 |
| abstract_inverted_index.inequalities | 123 |
| abstract_inverted_index.perspective, | 103 |
| abstract_inverted_index.approximation | 11 |
| abstract_inverted_index.concentration | 122 |
| abstract_inverted_index.interactions. | 70 |
| abstract_inverted_index.reinforcement | 6, 39 |
| abstract_inverted_index.approximation; | 29 |
| abstract_inverted_index.dimensionality | 55 |
| abstract_inverted_index.methodological | 74 |
| abstract_inverted_index.value-targeted | 100 |
| abstract_inverted_index.prior-dependent | 21 |
| abstract_inverted_index.$\mathcal{O}(\sqrt{\log | 79 |
| abstract_inverted_index.${\mathcal{O}}(d\sqrt{H^3 | 47 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile |