Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning With Shapley Values Article Swipe
Alexandre Heuillet
,
Fabien Couthouis
,
Natalia Díaz-Rodríguez
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1109/mci.2021.3129959
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1109/mci.2021.3129959
While Explainable Artificial Intelligence (XAI) is increasingly expanding more areas of application, little has been applied to make deep Reinforcement Learning (RL) more comprehensible. As RL becomes ubiquitous and used in critical and general public applications, it is essential to develop methods that make it better understood and more interpretable. This study proposes a novel approach to explain cooperative strategies in multiagent RL using Shapley values, a game theory concept used in XAI that successfully explains the rationale behind decisions taken by Machine Learning algorithms. Through testing common assumptions of this technique in two cooperation-centered socially challenging multi-agent environments environments, this article argues that Shapley values are a pertinent way to evaluate the contribution of players in a cooperative multi-agent RL context. To palliate the high overhead of this method, Shapley values are approximated using Monte Carlo sampling. Experimental results on Multiagent Particle and Sequential Social Dilemmas show that Shapley values succeed at estimating the contribution of each agent. These results could have implications that go beyond games in economics, (e.g., for non-discriminatory decision making, ethical and responsible AI-derived decisions or policy making under fairness constraints). They also expose how Shapley values only give general explanations about a model and cannot explain a single run, episode nor justify precise actions taken by agents. Future work should focus on addressing these critical aspects.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1109/mci.2021.3129959
- OA Status
- green
- Cited By
- 1
- References
- 43
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3201765467
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3201765467Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/mci.2021.3129959Digital Object Identifier
- Title
-
Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning With Shapley ValuesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-13Full publication date if available
- Authors
-
Alexandre Heuillet, Fabien Couthouis, Natalia Díaz-RodríguezList of authors in order
- Landing page
-
https://doi.org/10.1109/mci.2021.3129959Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2110.01307Direct OA link when available
- Concepts
-
Reinforcement learning, Computer science, Shapley value, Context (archaeology), Cooperative game theory, Artificial intelligence, Game theory, Mathematical economics, Management science, Operations research, Economics, Mathematics, Paleontology, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 1Per-year citation counts (last 5 years)
- References (count)
-
43Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3201765467 |
|---|---|
| doi | https://doi.org/10.1109/mci.2021.3129959 |
| ids.doi | https://doi.org/10.48550/arxiv.2110.01307 |
| ids.mag | 3201765467 |
| ids.openalex | https://openalex.org/W3201765467 |
| fwci | 0.19579882 |
| type | preprint |
| title | Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning With Shapley Values |
| biblio.issue | 1 |
| biblio.volume | 17 |
| biblio.last_page | 71 |
| biblio.first_page | 59 |
| topics[0].id | https://openalex.org/T12026 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9987000226974487 |
| 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 | Explainable Artificial Intelligence (XAI) |
| topics[1].id | https://openalex.org/T10883 |
| topics[1].field.id | https://openalex.org/fields/33 |
| topics[1].field.display_name | Social Sciences |
| topics[1].score | 0.9728000164031982 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3311 |
| topics[1].subfield.display_name | Safety Research |
| topics[1].display_name | Ethics and Social Impacts of AI |
| topics[2].id | https://openalex.org/T11674 |
| topics[2].field.id | https://openalex.org/fields/20 |
| topics[2].field.display_name | Economics, Econometrics and Finance |
| topics[2].score | 0.9538999795913696 |
| 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 | Sports Analytics and Performance |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C97541855 |
| concepts[0].level | 2 |
| concepts[0].score | 0.776532769203186 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q830687 |
| concepts[0].display_name | Reinforcement learning |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6806325912475586 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C199022921 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6018399000167847 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q240046 |
| concepts[2].display_name | Shapley value |
| concepts[3].id | https://openalex.org/C2779343474 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5896196365356445 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[3].display_name | Context (archaeology) |
| concepts[4].id | https://openalex.org/C2781416736 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5591351389884949 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q105354050 |
| concepts[4].display_name | Cooperative game theory |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4899060130119324 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C177142836 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4423588812351227 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q44455 |
| concepts[6].display_name | Game theory |
| concepts[7].id | https://openalex.org/C144237770 |
| concepts[7].level | 1 |
| concepts[7].score | 0.37721171975135803 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q747534 |
| concepts[7].display_name | Mathematical economics |
| concepts[8].id | https://openalex.org/C539667460 |
| concepts[8].level | 1 |
| concepts[8].score | 0.3466419577598572 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2414942 |
| concepts[8].display_name | Management science |
| concepts[9].id | https://openalex.org/C42475967 |
| concepts[9].level | 1 |
| concepts[9].score | 0.3296416401863098 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q194292 |
| concepts[9].display_name | Operations research |
| concepts[10].id | https://openalex.org/C162324750 |
| concepts[10].level | 0 |
| concepts[10].score | 0.1705576479434967 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[10].display_name | Economics |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.11575976014137268 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C151730666 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[12].display_name | Paleontology |
| concepts[13].id | https://openalex.org/C86803240 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[13].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/reinforcement-learning |
| keywords[0].score | 0.776532769203186 |
| keywords[0].display_name | Reinforcement learning |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6806325912475586 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/shapley-value |
| keywords[2].score | 0.6018399000167847 |
| keywords[2].display_name | Shapley value |
| keywords[3].id | https://openalex.org/keywords/context |
| keywords[3].score | 0.5896196365356445 |
| keywords[3].display_name | Context (archaeology) |
| keywords[4].id | https://openalex.org/keywords/cooperative-game-theory |
| keywords[4].score | 0.5591351389884949 |
| keywords[4].display_name | Cooperative game theory |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.4899060130119324 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/game-theory |
| keywords[6].score | 0.4423588812351227 |
| keywords[6].display_name | Game theory |
| keywords[7].id | https://openalex.org/keywords/mathematical-economics |
| keywords[7].score | 0.37721171975135803 |
| keywords[7].display_name | Mathematical economics |
| keywords[8].id | https://openalex.org/keywords/management-science |
| keywords[8].score | 0.3466419577598572 |
| keywords[8].display_name | Management science |
| keywords[9].id | https://openalex.org/keywords/operations-research |
| keywords[9].score | 0.3296416401863098 |
| keywords[9].display_name | Operations research |
| keywords[10].id | https://openalex.org/keywords/economics |
| keywords[10].score | 0.1705576479434967 |
| keywords[10].display_name | Economics |
| keywords[11].id | https://openalex.org/keywords/mathematics |
| keywords[11].score | 0.11575976014137268 |
| keywords[11].display_name | Mathematics |
| language | en |
| locations[0].id | doi:10.1109/mci.2021.3129959 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S104797584 |
| locations[0].source.issn | 1556-603X, 1556-6048 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1556-603X |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | IEEE Computational Intelligence Magazine |
| locations[0].source.host_organization | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_name | Institute of Electrical and Electronics Engineers |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319808 |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | IEEE Computational Intelligence Magazine |
| locations[0].landing_page_url | https://doi.org/10.1109/mci.2021.3129959 |
| locations[1].id | pmh:oai:arXiv.org:2110.01307 |
| 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 | https://arxiv.org/pdf/2110.01307 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2110.01307 |
| locations[2].id | mag:3201765467 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | arXiv (Cornell University) |
| locations[2].landing_page_url | http://export.arxiv.org/pdf/2110.01307 |
| locations[3].id | pmh:oai:HAL:hal-03549473v1 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306402512 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | False |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | HAL (Le Centre pour la Communication Scientifique Directe) |
| locations[3].source.host_organization | https://openalex.org/I1294671590 |
| locations[3].source.host_organization_name | Centre National de la Recherche Scientifique |
| locations[3].source.host_organization_lineage | https://openalex.org/I1294671590 |
| locations[3].license | other-oa |
| locations[3].pdf_url | |
| locations[3].version | submittedVersion |
| locations[3].raw_type | Journal articles |
| locations[3].license_id | https://openalex.org/licenses/other-oa |
| locations[3].is_accepted | False |
| locations[3].is_published | False |
| locations[3].raw_source_name | IEEE Computational Intelligence Magazine, 2022, 17 (1), pp.59-71. ⟨10.1109/MCI.2021.3129959⟩ |
| locations[3].landing_page_url | https://hal.science/hal-03549473 |
| locations[4].id | doi:10.48550/arxiv.2110.01307 |
| locations[4].is_oa | True |
| locations[4].source.id | https://openalex.org/S4306400194 |
| locations[4].source.issn | |
| locations[4].source.type | repository |
| locations[4].source.is_oa | True |
| locations[4].source.issn_l | |
| locations[4].source.is_core | False |
| locations[4].source.is_in_doaj | False |
| locations[4].source.display_name | arXiv (Cornell University) |
| locations[4].source.host_organization | https://openalex.org/I205783295 |
| locations[4].source.host_organization_name | Cornell University |
| locations[4].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[4].license | cc-by |
| locations[4].pdf_url | |
| locations[4].version | |
| locations[4].raw_type | article |
| locations[4].license_id | https://openalex.org/licenses/cc-by |
| locations[4].is_accepted | False |
| locations[4].is_published | |
| locations[4].raw_source_name | |
| locations[4].landing_page_url | https://doi.org/10.48550/arxiv.2110.01307 |
| indexed_in | arxiv, crossref, datacite |
| authorships[0].author.id | https://openalex.org/A5081018738 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-2109-7895 |
| authorships[0].author.display_name | Alexandre Heuillet |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Alexandre Heuillet |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5056322439 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5849-2616 |
| authorships[1].author.display_name | Fabien Couthouis |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Fabien Couthouis |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5058176171 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3362-9326 |
| authorships[2].author.display_name | Natalia Díaz-Rodríguez |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Natalia Díaz Rodríguez |
| authorships[2].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/2110.01307 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning With Shapley Values |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12026 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9987000226974487 |
| 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 | Explainable Artificial Intelligence (XAI) |
| related_works | https://openalex.org/W3091679651, https://openalex.org/W1168398685, https://openalex.org/W2080787648, https://openalex.org/W328418458, https://openalex.org/W2111603757, https://openalex.org/W2150814963, https://openalex.org/W2795912112, https://openalex.org/W108336744, https://openalex.org/W2133037279, https://openalex.org/W2205452926, https://openalex.org/W2909244445, https://openalex.org/W2012127258, https://openalex.org/W6891831, https://openalex.org/W2911743772, https://openalex.org/W3043022956, https://openalex.org/W1540728552, https://openalex.org/W1965020715, https://openalex.org/W2069137899, https://openalex.org/W2114156633, https://openalex.org/W3204828078 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 5 |
| best_oa_location.id | pmh:oai:arXiv.org:2110.01307 |
| 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/2110.01307 |
| 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/2110.01307 |
| primary_location.id | doi:10.1109/mci.2021.3129959 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S104797584 |
| primary_location.source.issn | 1556-603X, 1556-6048 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1556-603X |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | IEEE Computational Intelligence Magazine |
| primary_location.source.host_organization | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | IEEE Computational Intelligence Magazine |
| primary_location.landing_page_url | https://doi.org/10.1109/mci.2021.3129959 |
| publication_date | 2022-01-13 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2129888542, https://openalex.org/W2026348610, https://openalex.org/W2096124674, https://openalex.org/W2100635887, https://openalex.org/W2568887908, https://openalex.org/W1980329534, https://openalex.org/W6737947904, https://openalex.org/W3107871149, https://openalex.org/W2487898712, https://openalex.org/W3204294479, https://openalex.org/W2753514269, https://openalex.org/W6738796088, https://openalex.org/W6735011893, https://openalex.org/W2981731882, https://openalex.org/W6741436713, https://openalex.org/W3125069671, https://openalex.org/W2996514457, https://openalex.org/W2516809705, https://openalex.org/W3116073702, https://openalex.org/W3011806746, https://openalex.org/W2998004401, https://openalex.org/W3082925502, https://openalex.org/W2796215194, https://openalex.org/W6787359305, https://openalex.org/W3093433874, https://openalex.org/W6744123322, https://openalex.org/W2972122474, https://openalex.org/W6684921986, https://openalex.org/W2930863966, https://openalex.org/W3127561923, https://openalex.org/W2754517384, https://openalex.org/W3175853876, https://openalex.org/W2565610523, https://openalex.org/W2914351253, https://openalex.org/W3171853008, https://openalex.org/W3154431979, https://openalex.org/W3102824929, https://openalex.org/W149129625, https://openalex.org/W3034764457, https://openalex.org/W2282821441, https://openalex.org/W2623431351, https://openalex.org/W3025747022, https://openalex.org/W2962954781 |
| referenced_works_count | 43 |
| abstract_inverted_index.a | 53, 66, 107, 117, 197, 202 |
| abstract_inverted_index.As | 24 |
| abstract_inverted_index.RL | 25, 62, 120 |
| abstract_inverted_index.To | 122 |
| abstract_inverted_index.at | 152 |
| abstract_inverted_index.by | 81, 211 |
| abstract_inverted_index.go | 165 |
| abstract_inverted_index.in | 30, 60, 71, 92, 116, 168 |
| abstract_inverted_index.is | 5, 37 |
| abstract_inverted_index.it | 36, 44 |
| abstract_inverted_index.of | 10, 89, 114, 127, 156 |
| abstract_inverted_index.on | 140, 217 |
| abstract_inverted_index.or | 180 |
| abstract_inverted_index.to | 16, 39, 56, 110 |
| abstract_inverted_index.XAI | 72 |
| abstract_inverted_index.and | 28, 32, 47, 143, 176, 199 |
| abstract_inverted_index.are | 106, 132 |
| abstract_inverted_index.for | 171 |
| abstract_inverted_index.has | 13 |
| abstract_inverted_index.how | 189 |
| abstract_inverted_index.nor | 206 |
| abstract_inverted_index.the | 76, 112, 124, 154 |
| abstract_inverted_index.two | 93 |
| abstract_inverted_index.way | 109 |
| abstract_inverted_index.(RL) | 21 |
| abstract_inverted_index.They | 186 |
| abstract_inverted_index.This | 50 |
| abstract_inverted_index.also | 187 |
| abstract_inverted_index.been | 14 |
| abstract_inverted_index.deep | 18 |
| abstract_inverted_index.each | 157 |
| abstract_inverted_index.game | 67 |
| abstract_inverted_index.give | 193 |
| abstract_inverted_index.have | 162 |
| abstract_inverted_index.high | 125 |
| abstract_inverted_index.make | 17, 43 |
| abstract_inverted_index.more | 8, 22, 48 |
| abstract_inverted_index.only | 192 |
| abstract_inverted_index.run, | 204 |
| abstract_inverted_index.show | 147 |
| abstract_inverted_index.that | 42, 73, 103, 148, 164 |
| abstract_inverted_index.this | 90, 100, 128 |
| abstract_inverted_index.used | 29, 70 |
| abstract_inverted_index.work | 214 |
| abstract_inverted_index.(XAI) | 4 |
| abstract_inverted_index.Carlo | 136 |
| abstract_inverted_index.Monte | 135 |
| abstract_inverted_index.These | 159 |
| abstract_inverted_index.While | 0 |
| abstract_inverted_index.about | 196 |
| abstract_inverted_index.areas | 9 |
| abstract_inverted_index.could | 161 |
| abstract_inverted_index.focus | 216 |
| abstract_inverted_index.games | 167 |
| abstract_inverted_index.model | 198 |
| abstract_inverted_index.novel | 54 |
| abstract_inverted_index.study | 51 |
| abstract_inverted_index.taken | 80, 210 |
| abstract_inverted_index.these | 219 |
| abstract_inverted_index.under | 183 |
| abstract_inverted_index.using | 63, 134 |
| abstract_inverted_index.(e.g., | 170 |
| abstract_inverted_index.Future | 213 |
| abstract_inverted_index.Social | 145 |
| abstract_inverted_index.agent. | 158 |
| abstract_inverted_index.argues | 102 |
| abstract_inverted_index.behind | 78 |
| abstract_inverted_index.better | 45 |
| abstract_inverted_index.beyond | 166 |
| abstract_inverted_index.cannot | 200 |
| abstract_inverted_index.common | 87 |
| abstract_inverted_index.expose | 188 |
| abstract_inverted_index.little | 12 |
| abstract_inverted_index.making | 182 |
| abstract_inverted_index.policy | 181 |
| abstract_inverted_index.public | 34 |
| abstract_inverted_index.should | 215 |
| abstract_inverted_index.single | 203 |
| abstract_inverted_index.theory | 68 |
| abstract_inverted_index.values | 105, 131, 150, 191 |
| abstract_inverted_index.Machine | 82 |
| abstract_inverted_index.Shapley | 64, 104, 130, 149, 190 |
| abstract_inverted_index.Through | 85 |
| abstract_inverted_index.actions | 209 |
| abstract_inverted_index.agents. | 212 |
| abstract_inverted_index.applied | 15 |
| abstract_inverted_index.article | 101 |
| abstract_inverted_index.becomes | 26 |
| abstract_inverted_index.concept | 69 |
| abstract_inverted_index.develop | 40 |
| abstract_inverted_index.episode | 205 |
| abstract_inverted_index.ethical | 175 |
| abstract_inverted_index.explain | 57, 201 |
| abstract_inverted_index.general | 33, 194 |
| abstract_inverted_index.justify | 207 |
| abstract_inverted_index.making, | 174 |
| abstract_inverted_index.method, | 129 |
| abstract_inverted_index.methods | 41 |
| abstract_inverted_index.players | 115 |
| abstract_inverted_index.precise | 208 |
| abstract_inverted_index.results | 139, 160 |
| abstract_inverted_index.succeed | 151 |
| abstract_inverted_index.testing | 86 |
| abstract_inverted_index.values, | 65 |
| abstract_inverted_index.Dilemmas | 146 |
| abstract_inverted_index.Learning | 20, 83 |
| abstract_inverted_index.Particle | 142 |
| abstract_inverted_index.approach | 55 |
| abstract_inverted_index.aspects. | 221 |
| abstract_inverted_index.context. | 121 |
| abstract_inverted_index.critical | 31, 220 |
| abstract_inverted_index.decision | 173 |
| abstract_inverted_index.evaluate | 111 |
| abstract_inverted_index.explains | 75 |
| abstract_inverted_index.fairness | 184 |
| abstract_inverted_index.overhead | 126 |
| abstract_inverted_index.palliate | 123 |
| abstract_inverted_index.proposes | 52 |
| abstract_inverted_index.socially | 95 |
| abstract_inverted_index.decisions | 79, 179 |
| abstract_inverted_index.essential | 38 |
| abstract_inverted_index.expanding | 7 |
| abstract_inverted_index.pertinent | 108 |
| abstract_inverted_index.rationale | 77 |
| abstract_inverted_index.sampling. | 137 |
| abstract_inverted_index.technique | 91 |
| abstract_inverted_index.AI-derived | 178 |
| abstract_inverted_index.Artificial | 2 |
| abstract_inverted_index.Multiagent | 141 |
| abstract_inverted_index.Sequential | 144 |
| abstract_inverted_index.addressing | 218 |
| abstract_inverted_index.economics, | 169 |
| abstract_inverted_index.estimating | 153 |
| abstract_inverted_index.multiagent | 61 |
| abstract_inverted_index.strategies | 59 |
| abstract_inverted_index.ubiquitous | 27 |
| abstract_inverted_index.understood | 46 |
| abstract_inverted_index.Explainable | 1 |
| abstract_inverted_index.algorithms. | 84 |
| abstract_inverted_index.assumptions | 88 |
| abstract_inverted_index.challenging | 96 |
| abstract_inverted_index.cooperative | 58, 118 |
| abstract_inverted_index.multi-agent | 97, 119 |
| abstract_inverted_index.responsible | 177 |
| abstract_inverted_index.Experimental | 138 |
| abstract_inverted_index.Intelligence | 3 |
| abstract_inverted_index.application, | 11 |
| abstract_inverted_index.approximated | 133 |
| abstract_inverted_index.contribution | 113, 155 |
| abstract_inverted_index.environments | 98 |
| abstract_inverted_index.explanations | 195 |
| abstract_inverted_index.implications | 163 |
| abstract_inverted_index.increasingly | 6 |
| abstract_inverted_index.successfully | 74 |
| abstract_inverted_index.Reinforcement | 19 |
| abstract_inverted_index.applications, | 35 |
| abstract_inverted_index.constraints). | 185 |
| abstract_inverted_index.environments, | 99 |
| abstract_inverted_index.interpretable. | 49 |
| abstract_inverted_index.comprehensible. | 23 |
| abstract_inverted_index.non-discriminatory | 172 |
| abstract_inverted_index.cooperation-centered | 94 |
| cited_by_percentile_year.max | 94 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.550000011920929 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile.value | 0.48825745 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |