Efficient Online Reinforcement Learning with Offline Data Article Swipe
Philip Ball
,
Laura Smith
,
Ilya Kostrikov
,
Sergey Levine
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2302.02948
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2302.02948
Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human expert or a sub-optimal exploration policy. Previous methods have relied on extensive modifications and additional complexity to ensure the effective use of this data. Instead, we ask: can we simply apply existing off-policy methods to leverage offline data when learning online? In this work, we demonstrate that the answer is yes; however, a set of minimal but important changes to existing off-policy RL algorithms are required to achieve reliable performance. We extensively ablate these design choices, demonstrating the key factors that most affect performance, and arrive at a set of recommendations that practitioners can readily apply, whether their data comprise a small number of expert demonstrations or large volumes of sub-optimal trajectories. We see that correct application of these simple recommendations can provide a $\mathbf{2.5\times}$ improvement over existing approaches across a diverse set of competitive benchmarks, with no additional computational overhead. We have released our code at https://github.com/ikostrikov/rlpd.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2302.02948
- https://arxiv.org/pdf/2302.02948
- OA Status
- green
- Cited By
- 13
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4319453704
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4319453704Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2302.02948Digital Object Identifier
- Title
-
Efficient Online Reinforcement Learning with Offline DataWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-02-06Full publication date if available
- Authors
-
Philip Ball, Laura Smith, Ilya Kostrikov, Sergey LevineList of authors in order
- Landing page
-
https://arxiv.org/abs/2302.02948Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2302.02948Direct 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/2302.02948Direct OA link when available
- Concepts
-
Computer science, Reinforcement learning, Leverage (statistics), Ask price, Overhead (engineering), Set (abstract data type), Machine learning, Key (lock), Artificial intelligence, Computer security, Operating system, Programming language, Economics, EconomyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
13Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2, 2024: 7, 2023: 4Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4319453704 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2302.02948 |
| ids.doi | https://doi.org/10.48550/arxiv.2302.02948 |
| ids.openalex | https://openalex.org/W4319453704 |
| fwci | |
| type | preprint |
| title | Efficient Online Reinforcement Learning with Offline Data |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10462 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9990000128746033 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Reinforcement Learning in Robotics |
| topics[1].id | https://openalex.org/T11704 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9940000176429749 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1706 |
| topics[1].subfield.display_name | Computer Science Applications |
| topics[1].display_name | Mobile Crowdsensing and Crowdsourcing |
| topics[2].id | https://openalex.org/T12288 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.988099992275238 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1705 |
| topics[2].subfield.display_name | Computer Networks and Communications |
| topics[2].display_name | Optimization and Search Problems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8394178152084351 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C97541855 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8180878162384033 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q830687 |
| concepts[1].display_name | Reinforcement learning |
| concepts[2].id | https://openalex.org/C153083717 |
| concepts[2].level | 2 |
| concepts[2].score | 0.8095667958259583 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q6535263 |
| concepts[2].display_name | Leverage (statistics) |
| concepts[3].id | https://openalex.org/C90329073 |
| concepts[3].level | 2 |
| concepts[3].score | 0.629267692565918 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q914232 |
| concepts[3].display_name | Ask price |
| concepts[4].id | https://openalex.org/C2779960059 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5580694675445557 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7113681 |
| concepts[4].display_name | Overhead (engineering) |
| concepts[5].id | https://openalex.org/C177264268 |
| concepts[5].level | 2 |
| concepts[5].score | 0.555311381816864 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[5].display_name | Set (abstract data type) |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.5468539595603943 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C26517878 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5118419528007507 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q228039 |
| concepts[7].display_name | Key (lock) |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.4637819528579712 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C38652104 |
| concepts[9].level | 1 |
| concepts[9].score | 0.12170276045799255 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[9].display_name | Computer security |
| concepts[10].id | https://openalex.org/C111919701 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[10].display_name | Operating system |
| concepts[11].id | https://openalex.org/C199360897 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[11].display_name | Programming language |
| concepts[12].id | https://openalex.org/C162324750 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[12].display_name | Economics |
| concepts[13].id | https://openalex.org/C136264566 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q159810 |
| concepts[13].display_name | Economy |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8394178152084351 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/reinforcement-learning |
| keywords[1].score | 0.8180878162384033 |
| keywords[1].display_name | Reinforcement learning |
| keywords[2].id | https://openalex.org/keywords/leverage |
| keywords[2].score | 0.8095667958259583 |
| keywords[2].display_name | Leverage (statistics) |
| keywords[3].id | https://openalex.org/keywords/ask-price |
| keywords[3].score | 0.629267692565918 |
| keywords[3].display_name | Ask price |
| keywords[4].id | https://openalex.org/keywords/overhead |
| keywords[4].score | 0.5580694675445557 |
| keywords[4].display_name | Overhead (engineering) |
| keywords[5].id | https://openalex.org/keywords/set |
| keywords[5].score | 0.555311381816864 |
| keywords[5].display_name | Set (abstract data type) |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.5468539595603943 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/key |
| keywords[7].score | 0.5118419528007507 |
| keywords[7].display_name | Key (lock) |
| keywords[8].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[8].score | 0.4637819528579712 |
| keywords[8].display_name | Artificial intelligence |
| keywords[9].id | https://openalex.org/keywords/computer-security |
| keywords[9].score | 0.12170276045799255 |
| keywords[9].display_name | Computer security |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2302.02948 |
| 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/2302.02948 |
| 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/2302.02948 |
| locations[1].id | doi:10.48550/arxiv.2302.02948 |
| 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.2302.02948 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5008365801 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5896-6447 |
| authorships[0].author.display_name | Philip Ball |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ball, Philip J. |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5106821653 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-7890-497X |
| authorships[1].author.display_name | Laura Smith |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Smith, Laura |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5086657309 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Ilya Kostrikov |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kostrikov, Ilya |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5026322200 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6764-2743 |
| authorships[3].author.display_name | Sergey Levine |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Levine, Sergey |
| 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/2302.02948 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Efficient Online Reinforcement Learning with Offline Data |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10462 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9990000128746033 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Reinforcement Learning in Robotics |
| related_works | https://openalex.org/W2168627904, https://openalex.org/W2515552481, https://openalex.org/W156769215, https://openalex.org/W1570348318, https://openalex.org/W2015444353, https://openalex.org/W3013494979, https://openalex.org/W4308101915, https://openalex.org/W3194047734, https://openalex.org/W2251005117, https://openalex.org/W2768698792 |
| cited_by_count | 13 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 7 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 4 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2302.02948 |
| 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/2302.02948 |
| 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/2302.02948 |
| primary_location.id | pmh:oai:arXiv.org:2302.02948 |
| 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/2302.02948 |
| 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/2302.02948 |
| publication_date | 2023-02-06 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.A | 12 |
| abstract_inverted_index.a | 34, 38, 88, 123, 136, 159, 166 |
| abstract_inverted_index.In | 77 |
| abstract_inverted_index.RL | 98 |
| abstract_inverted_index.We | 106, 148, 177 |
| abstract_inverted_index.as | 30 |
| abstract_inverted_index.at | 122, 182 |
| abstract_inverted_index.be | 17 |
| abstract_inverted_index.in | 7 |
| abstract_inverted_index.is | 23, 85 |
| abstract_inverted_index.no | 173 |
| abstract_inverted_index.of | 26, 57, 90, 125, 139, 145, 153, 169 |
| abstract_inverted_index.on | 46 |
| abstract_inverted_index.or | 37, 142 |
| abstract_inverted_index.to | 19, 52, 70, 95, 102 |
| abstract_inverted_index.we | 61, 64, 80 |
| abstract_inverted_index.and | 2, 49, 120 |
| abstract_inverted_index.are | 100 |
| abstract_inverted_index.but | 92 |
| abstract_inverted_index.can | 16, 63, 129, 157 |
| abstract_inverted_index.key | 114 |
| abstract_inverted_index.our | 180 |
| abstract_inverted_index.see | 149 |
| abstract_inverted_index.set | 89, 124, 168 |
| abstract_inverted_index.the | 24, 54, 83, 113 |
| abstract_inverted_index.use | 56 |
| abstract_inverted_index.ask: | 62 |
| abstract_inverted_index.code | 181 |
| abstract_inverted_index.data | 73, 134 |
| abstract_inverted_index.from | 33 |
| abstract_inverted_index.have | 44, 178 |
| abstract_inverted_index.most | 117 |
| abstract_inverted_index.over | 162 |
| abstract_inverted_index.such | 29 |
| abstract_inverted_index.that | 15, 82, 116, 127, 150 |
| abstract_inverted_index.this | 58, 78 |
| abstract_inverted_index.when | 74 |
| abstract_inverted_index.with | 172 |
| abstract_inverted_index.yes; | 86 |
| abstract_inverted_index.(RL). | 11 |
| abstract_inverted_index.apply | 66 |
| abstract_inverted_index.data, | 28 |
| abstract_inverted_index.data. | 59 |
| abstract_inverted_index.human | 35 |
| abstract_inverted_index.large | 143 |
| abstract_inverted_index.major | 5 |
| abstract_inverted_index.prior | 31 |
| abstract_inverted_index.small | 137 |
| abstract_inverted_index.their | 133 |
| abstract_inverted_index.these | 21, 109, 154 |
| abstract_inverted_index.work, | 79 |
| abstract_inverted_index.Sample | 0 |
| abstract_inverted_index.ablate | 108 |
| abstract_inverted_index.across | 165 |
| abstract_inverted_index.affect | 118 |
| abstract_inverted_index.answer | 84 |
| abstract_inverted_index.apply, | 131 |
| abstract_inverted_index.arrive | 121 |
| abstract_inverted_index.design | 110 |
| abstract_inverted_index.ensure | 53 |
| abstract_inverted_index.expert | 36, 140 |
| abstract_inverted_index.issues | 22 |
| abstract_inverted_index.number | 138 |
| abstract_inverted_index.online | 8 |
| abstract_inverted_index.relied | 45 |
| abstract_inverted_index.remain | 4 |
| abstract_inverted_index.simple | 155 |
| abstract_inverted_index.simply | 65 |
| abstract_inverted_index.achieve | 103 |
| abstract_inverted_index.address | 20 |
| abstract_inverted_index.applied | 18 |
| abstract_inverted_index.changes | 94 |
| abstract_inverted_index.correct | 151 |
| abstract_inverted_index.diverse | 167 |
| abstract_inverted_index.factors | 115 |
| abstract_inverted_index.methods | 43, 69 |
| abstract_inverted_index.minimal | 91 |
| abstract_inverted_index.offline | 27, 72 |
| abstract_inverted_index.online? | 76 |
| abstract_inverted_index.policy. | 41 |
| abstract_inverted_index.provide | 158 |
| abstract_inverted_index.readily | 130 |
| abstract_inverted_index.volumes | 144 |
| abstract_inverted_index.whether | 132 |
| abstract_inverted_index.Instead, | 60 |
| abstract_inverted_index.Previous | 42 |
| abstract_inverted_index.approach | 14 |
| abstract_inverted_index.choices, | 111 |
| abstract_inverted_index.comprise | 135 |
| abstract_inverted_index.existing | 67, 96, 163 |
| abstract_inverted_index.however, | 87 |
| abstract_inverted_index.learning | 10, 75 |
| abstract_inverted_index.leverage | 71 |
| abstract_inverted_index.powerful | 13 |
| abstract_inverted_index.released | 179 |
| abstract_inverted_index.reliable | 104 |
| abstract_inverted_index.required | 101 |
| abstract_inverted_index.effective | 55 |
| abstract_inverted_index.extensive | 47 |
| abstract_inverted_index.important | 93 |
| abstract_inverted_index.inclusion | 25 |
| abstract_inverted_index.overhead. | 176 |
| abstract_inverted_index.additional | 50, 174 |
| abstract_inverted_index.algorithms | 99 |
| abstract_inverted_index.approaches | 164 |
| abstract_inverted_index.challenges | 6 |
| abstract_inverted_index.complexity | 51 |
| abstract_inverted_index.efficiency | 1 |
| abstract_inverted_index.off-policy | 68, 97 |
| abstract_inverted_index.application | 152 |
| abstract_inverted_index.benchmarks, | 171 |
| abstract_inverted_index.competitive | 170 |
| abstract_inverted_index.demonstrate | 81 |
| abstract_inverted_index.exploration | 3, 40 |
| abstract_inverted_index.extensively | 107 |
| abstract_inverted_index.improvement | 161 |
| abstract_inverted_index.sub-optimal | 39, 146 |
| abstract_inverted_index.performance, | 119 |
| abstract_inverted_index.performance. | 105 |
| abstract_inverted_index.trajectories | 32 |
| abstract_inverted_index.computational | 175 |
| abstract_inverted_index.demonstrating | 112 |
| abstract_inverted_index.modifications | 48 |
| abstract_inverted_index.practitioners | 128 |
| abstract_inverted_index.reinforcement | 9 |
| abstract_inverted_index.trajectories. | 147 |
| abstract_inverted_index.demonstrations | 141 |
| abstract_inverted_index.recommendations | 126, 156 |
| abstract_inverted_index.$\mathbf{2.5\times}$ | 160 |
| abstract_inverted_index.https://github.com/ikostrikov/rlpd. | 183 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/17 |
| sustainable_development_goals[0].score | 0.4000000059604645 |
| sustainable_development_goals[0].display_name | Partnerships for the goals |
| citation_normalized_percentile |