Reliable Off-Policy Learning for Dosage Combinations Article Swipe
Jonas Schweisthal
,
Dennis Frauen
,
Valentyn Melnychuk
,
Stefan Feuerriegel
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2305.19742
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2305.19742
Decision-making in personalized medicine such as cancer therapy or critical care must often make choices for dosage combinations, i.e., multiple continuous treatments. Existing work for this task has modeled the effect of multiple treatments independently, while estimating the joint effect has received little attention but comes with non-trivial challenges. In this paper, we propose a novel method for reliable off-policy learning for dosage combinations. Our method proceeds along three steps: (1) We develop a tailored neural network that estimates the individualized dose-response function while accounting for the joint effect of multiple dependent dosages. (2) We estimate the generalized propensity score using conditional normalizing flows in order to detect regions with limited overlap in the shared covariate-treatment space. (3) We present a gradient-based learning algorithm to find the optimal, individualized dosage combinations. Here, we ensure reliable estimation of the policy value by avoiding regions with limited overlap. We finally perform an extensive evaluation of our method to show its effectiveness. To the best of our knowledge, ours is the first work to provide a method for reliable off-policy learning for optimal dosage combinations.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2305.19742
- https://arxiv.org/pdf/2305.19742
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4379087843
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4379087843Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2305.19742Digital Object Identifier
- Title
-
Reliable Off-Policy Learning for Dosage CombinationsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-05-31Full publication date if available
- Authors
-
Jonas Schweisthal, Dennis Frauen, Valentyn Melnychuk, Stefan FeuerriegelList of authors in order
- Landing page
-
https://arxiv.org/abs/2305.19742Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2305.19742Direct 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/2305.19742Direct OA link when available
- Concepts
-
Computer science, Covariate, Artificial neural network, Machine learning, Task (project management), Function (biology), Artificial intelligence, Evolutionary biology, Economics, Management, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4379087843 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2305.19742 |
| ids.doi | https://doi.org/10.48550/arxiv.2305.19742 |
| ids.openalex | https://openalex.org/W4379087843 |
| fwci | |
| type | preprint |
| title | Reliable Off-Policy Learning for Dosage Combinations |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11235 |
| topics[0].field.id | https://openalex.org/fields/26 |
| topics[0].field.display_name | Mathematics |
| topics[0].score | 0.9950000047683716 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2613 |
| topics[0].subfield.display_name | Statistics and Probability |
| topics[0].display_name | Statistical Methods in Clinical Trials |
| topics[1].id | https://openalex.org/T10845 |
| topics[1].field.id | https://openalex.org/fields/26 |
| topics[1].field.display_name | Mathematics |
| topics[1].score | 0.9810000061988831 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2613 |
| topics[1].subfield.display_name | Statistics and Probability |
| topics[1].display_name | Advanced Causal Inference Techniques |
| topics[2].id | https://openalex.org/T10804 |
| topics[2].field.id | https://openalex.org/fields/20 |
| topics[2].field.display_name | Economics, Econometrics and Finance |
| topics[2].score | 0.9715999960899353 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2002 |
| topics[2].subfield.display_name | Economics and Econometrics |
| topics[2].display_name | Health Systems, Economic Evaluations, Quality of Life |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6223198771476746 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C119043178 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6202647686004639 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q320723 |
| concepts[1].display_name | Covariate |
| concepts[2].id | https://openalex.org/C50644808 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5299690365791321 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[2].display_name | Artificial neural network |
| concepts[3].id | https://openalex.org/C119857082 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5203192234039307 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C2780451532 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5134676098823547 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[4].display_name | Task (project management) |
| concepts[5].id | https://openalex.org/C14036430 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4501101076602936 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q3736076 |
| concepts[5].display_name | Function (biology) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.44440558552742004 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C78458016 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q840400 |
| concepts[7].display_name | Evolutionary biology |
| concepts[8].id | https://openalex.org/C162324750 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[8].display_name | Economics |
| concepts[9].id | https://openalex.org/C187736073 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[9].display_name | Management |
| concepts[10].id | https://openalex.org/C86803240 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[10].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6223198771476746 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/covariate |
| keywords[1].score | 0.6202647686004639 |
| keywords[1].display_name | Covariate |
| keywords[2].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[2].score | 0.5299690365791321 |
| keywords[2].display_name | Artificial neural network |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.5203192234039307 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/task |
| keywords[4].score | 0.5134676098823547 |
| keywords[4].display_name | Task (project management) |
| keywords[5].id | https://openalex.org/keywords/function |
| keywords[5].score | 0.4501101076602936 |
| keywords[5].display_name | Function (biology) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.44440558552742004 |
| keywords[6].display_name | Artificial intelligence |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2305.19742 |
| 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/2305.19742 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2305.19742 |
| locations[1].id | doi:10.48550/arxiv.2305.19742 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2305.19742 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5072558230 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3725-3821 |
| authorships[0].author.display_name | Jonas Schweisthal |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Schweisthal, Jonas |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5060813780 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6526-1162 |
| authorships[1].author.display_name | Dennis Frauen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Frauen, Dennis |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5012167803 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2401-6803 |
| authorships[2].author.display_name | Valentyn Melnychuk |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Melnychuk, Valentyn |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5081442873 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-7856-8729 |
| authorships[3].author.display_name | Stefan Feuerriegel |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Feuerriegel, Stefan |
| authorships[3].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/2305.19742 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Reliable Off-Policy Learning for Dosage Combinations |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11235 |
| primary_topic.field.id | https://openalex.org/fields/26 |
| primary_topic.field.display_name | Mathematics |
| primary_topic.score | 0.9950000047683716 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2613 |
| primary_topic.subfield.display_name | Statistics and Probability |
| primary_topic.display_name | Statistical Methods in Clinical Trials |
| related_works | https://openalex.org/W2985746494, https://openalex.org/W4206042385, https://openalex.org/W2511384863, https://openalex.org/W2080773131, https://openalex.org/W2096089271, https://openalex.org/W2923628599, https://openalex.org/W2014100433, https://openalex.org/W2051519658, https://openalex.org/W2994787386, https://openalex.org/W2002304499 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2305.19742 |
| 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/2305.19742 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2305.19742 |
| primary_location.id | pmh:oai:arXiv.org:2305.19742 |
| 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/2305.19742 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2305.19742 |
| publication_date | 2023-05-31 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 54, 73, 120, 172 |
| abstract_inverted_index.In | 49 |
| abstract_inverted_index.To | 159 |
| abstract_inverted_index.We | 71, 94, 118, 146 |
| abstract_inverted_index.an | 149 |
| abstract_inverted_index.as | 5 |
| abstract_inverted_index.by | 140 |
| abstract_inverted_index.in | 1, 104, 112 |
| abstract_inverted_index.is | 166 |
| abstract_inverted_index.of | 31, 89, 136, 152, 162 |
| abstract_inverted_index.or | 8 |
| abstract_inverted_index.to | 106, 124, 155, 170 |
| abstract_inverted_index.we | 52, 132 |
| abstract_inverted_index.(1) | 70 |
| abstract_inverted_index.(2) | 93 |
| abstract_inverted_index.(3) | 117 |
| abstract_inverted_index.Our | 64 |
| abstract_inverted_index.but | 44 |
| abstract_inverted_index.for | 15, 24, 57, 61, 85, 174, 178 |
| abstract_inverted_index.has | 27, 40 |
| abstract_inverted_index.its | 157 |
| abstract_inverted_index.our | 153, 163 |
| abstract_inverted_index.the | 29, 37, 79, 86, 96, 113, 126, 137, 160, 167 |
| abstract_inverted_index.best | 161 |
| abstract_inverted_index.care | 10 |
| abstract_inverted_index.find | 125 |
| abstract_inverted_index.make | 13 |
| abstract_inverted_index.must | 11 |
| abstract_inverted_index.ours | 165 |
| abstract_inverted_index.show | 156 |
| abstract_inverted_index.such | 4 |
| abstract_inverted_index.task | 26 |
| abstract_inverted_index.that | 77 |
| abstract_inverted_index.this | 25, 50 |
| abstract_inverted_index.with | 46, 109, 143 |
| abstract_inverted_index.work | 23, 169 |
| abstract_inverted_index.Here, | 131 |
| abstract_inverted_index.along | 67 |
| abstract_inverted_index.comes | 45 |
| abstract_inverted_index.first | 168 |
| abstract_inverted_index.flows | 103 |
| abstract_inverted_index.i.e., | 18 |
| abstract_inverted_index.joint | 38, 87 |
| abstract_inverted_index.novel | 55 |
| abstract_inverted_index.often | 12 |
| abstract_inverted_index.order | 105 |
| abstract_inverted_index.score | 99 |
| abstract_inverted_index.three | 68 |
| abstract_inverted_index.using | 100 |
| abstract_inverted_index.value | 139 |
| abstract_inverted_index.while | 35, 83 |
| abstract_inverted_index.cancer | 6 |
| abstract_inverted_index.detect | 107 |
| abstract_inverted_index.dosage | 16, 62, 129, 180 |
| abstract_inverted_index.effect | 30, 39, 88 |
| abstract_inverted_index.ensure | 133 |
| abstract_inverted_index.little | 42 |
| abstract_inverted_index.method | 56, 65, 154, 173 |
| abstract_inverted_index.neural | 75 |
| abstract_inverted_index.paper, | 51 |
| abstract_inverted_index.policy | 138 |
| abstract_inverted_index.shared | 114 |
| abstract_inverted_index.space. | 116 |
| abstract_inverted_index.steps: | 69 |
| abstract_inverted_index.choices | 14 |
| abstract_inverted_index.develop | 72 |
| abstract_inverted_index.finally | 147 |
| abstract_inverted_index.limited | 110, 144 |
| abstract_inverted_index.modeled | 28 |
| abstract_inverted_index.network | 76 |
| abstract_inverted_index.optimal | 179 |
| abstract_inverted_index.overlap | 111 |
| abstract_inverted_index.perform | 148 |
| abstract_inverted_index.present | 119 |
| abstract_inverted_index.propose | 53 |
| abstract_inverted_index.provide | 171 |
| abstract_inverted_index.regions | 108, 142 |
| abstract_inverted_index.therapy | 7 |
| abstract_inverted_index.Existing | 22 |
| abstract_inverted_index.avoiding | 141 |
| abstract_inverted_index.critical | 9 |
| abstract_inverted_index.dosages. | 92 |
| abstract_inverted_index.estimate | 95 |
| abstract_inverted_index.function | 82 |
| abstract_inverted_index.learning | 60, 122, 177 |
| abstract_inverted_index.medicine | 3 |
| abstract_inverted_index.multiple | 19, 32, 90 |
| abstract_inverted_index.optimal, | 127 |
| abstract_inverted_index.overlap. | 145 |
| abstract_inverted_index.proceeds | 66 |
| abstract_inverted_index.received | 41 |
| abstract_inverted_index.reliable | 58, 134, 175 |
| abstract_inverted_index.tailored | 74 |
| abstract_inverted_index.algorithm | 123 |
| abstract_inverted_index.attention | 43 |
| abstract_inverted_index.dependent | 91 |
| abstract_inverted_index.estimates | 78 |
| abstract_inverted_index.extensive | 150 |
| abstract_inverted_index.accounting | 84 |
| abstract_inverted_index.continuous | 20 |
| abstract_inverted_index.estimating | 36 |
| abstract_inverted_index.estimation | 135 |
| abstract_inverted_index.evaluation | 151 |
| abstract_inverted_index.knowledge, | 164 |
| abstract_inverted_index.off-policy | 59, 176 |
| abstract_inverted_index.propensity | 98 |
| abstract_inverted_index.treatments | 33 |
| abstract_inverted_index.challenges. | 48 |
| abstract_inverted_index.conditional | 101 |
| abstract_inverted_index.generalized | 97 |
| abstract_inverted_index.non-trivial | 47 |
| abstract_inverted_index.normalizing | 102 |
| abstract_inverted_index.treatments. | 21 |
| abstract_inverted_index.personalized | 2 |
| abstract_inverted_index.combinations, | 17 |
| abstract_inverted_index.combinations. | 63, 130, 181 |
| abstract_inverted_index.dose-response | 81 |
| abstract_inverted_index.effectiveness. | 158 |
| abstract_inverted_index.gradient-based | 121 |
| abstract_inverted_index.independently, | 34 |
| abstract_inverted_index.individualized | 80, 128 |
| abstract_inverted_index.Decision-making | 0 |
| abstract_inverted_index.covariate-treatment | 115 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.6600000262260437 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |