Learning to Generate Natural Language Rationales for Game Playing Agents Article Swipe
YOU?
·
· 2018
· Open Access
·
Many computer games feature non-player charactert (NPC) teammates and companions; however, playing with or against NPCs can be frustrating when they perform unexpectedly. These frustrations can be avoided if the NPC has the ability to explain its actions and motivations. When NPC behavior is controlled by a black box AI system it can be hard to generate the necessary explanations. In this paper, we present a system that generates human-like, natural language explanations—called rationales—of an agent's actions in a game environment regardless of how the decisions are made by a black box AI. We outline a robust data collection and neural network training pipeline that can be used to gather think-aloud data and train a rationale generation model for any similar sequential turn based decision making task. A human-subject study shows that our technique produces believable rationales for an agent playing the game, Frogger. We conclude with insights about how people perceive automatically generated rationales.
Related Topics
- Type
- article
- Language
- en
- Landing Page
- https://uknowledge.uky.edu/cs_facpub/18
- https://uknowledge.uky.edu/cs_facpub/18
- OA Status
- green
- Cited By
- 2
- References
- 10
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W2913958482
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2913958482Canonical identifier for this work in OpenAlex
- Title
-
Learning to Generate Natural Language Rationales for Game Playing AgentsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2018Year of publication
- Publication date
-
2018-01-01Full publication date if available
- Authors
-
Upol Ehsan, Pradyumna Tambwekar, Larry Chan, Brent Harrison, Mark RiedlList of authors in order
- Landing page
-
https://uknowledge.uky.edu/cs_facpub/18Publisher landing page
- PDF URL
-
https://uknowledge.uky.edu/cs_facpub/18Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://uknowledge.uky.edu/cs_facpub/18Direct OA link when available
- Concepts
-
Natural (archaeology), Computer science, Natural language, Artificial intelligence, Natural language processing, History, ArchaeologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 1, 2021: 1Per-year citation counts (last 5 years)
- References (count)
-
10Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2913958482 |
|---|---|
| doi | |
| ids.mag | 2913958482 |
| ids.openalex | https://openalex.org/W2913958482 |
| fwci | 0.19856246 |
| type | article |
| title | Learning to Generate Natural Language Rationales for Game Playing Agents |
| biblio.issue | 122 |
| biblio.volume | 2282 |
| biblio.last_page | |
| biblio.first_page | 1 |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9988999962806702 |
| 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 | Topic Modeling |
| topics[1].id | https://openalex.org/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.996999979019165 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T11574 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9939000010490417 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Artificial Intelligence in Games |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2776608160 |
| concepts[0].level | 2 |
| concepts[0].score | 0.5943776965141296 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q4785462 |
| concepts[0].display_name | Natural (archaeology) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.545782208442688 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C195324797 |
| concepts[2].level | 2 |
| concepts[2].score | 0.44389185309410095 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q33742 |
| concepts[2].display_name | Natural language |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.3474486768245697 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C204321447 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3379271328449249 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[4].display_name | Natural language processing |
| concepts[5].id | https://openalex.org/C95457728 |
| concepts[5].level | 0 |
| concepts[5].score | 0.1456320881843567 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q309 |
| concepts[5].display_name | History |
| concepts[6].id | https://openalex.org/C166957645 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[6].display_name | Archaeology |
| keywords[0].id | https://openalex.org/keywords/natural |
| keywords[0].score | 0.5943776965141296 |
| keywords[0].display_name | Natural (archaeology) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.545782208442688 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/natural-language |
| keywords[2].score | 0.44389185309410095 |
| keywords[2].display_name | Natural language |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.3474486768245697 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/natural-language-processing |
| keywords[4].score | 0.3379271328449249 |
| keywords[4].display_name | Natural language processing |
| keywords[5].id | https://openalex.org/keywords/history |
| keywords[5].score | 0.1456320881843567 |
| keywords[5].display_name | History |
| language | en |
| locations[0].id | pmh:oai:uknowledge.uky.edu:cs_facpub-1017 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306402622 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | UKnowledge (University of Kentucky) |
| locations[0].source.host_organization | https://openalex.org/I143302722 |
| locations[0].source.host_organization_name | University of Kentucky |
| locations[0].source.host_organization_lineage | https://openalex.org/I143302722 |
| locations[0].license | |
| locations[0].pdf_url | https://uknowledge.uky.edu/cs_facpub/18 |
| 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 | Computer Science Faculty Publications |
| locations[0].landing_page_url | https://uknowledge.uky.edu/cs_facpub/18 |
| locations[1].id | mag:2913958482 |
| locations[1].is_oa | False |
| locations[1].source | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://ceur-ws.org/Vol-2282/EXAG_122.pdf |
| authorships[0].author.id | https://openalex.org/A5010875544 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-4911-0409 |
| authorships[0].author.display_name | Upol Ehsan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Upol Ehsan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5051331381 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2931-2502 |
| authorships[1].author.display_name | Pradyumna Tambwekar |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Pradyumna Tambwekar |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5088617975 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Larry Chan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Larry Chan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5047163199 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-1301-5928 |
| authorships[3].author.display_name | Brent Harrison |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Brent Harrison |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5061883150 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-5283-6588 |
| authorships[4].author.display_name | Mark Riedl |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Mark O. Riedl |
| authorships[4].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://uknowledge.uky.edu/cs_facpub/18 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning to Generate Natural Language Rationales for Game Playing Agents |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T04:12:42.849631 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9988999962806702 |
| 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 | Topic Modeling |
| related_works | https://openalex.org/W40448064, https://openalex.org/W2533645947, https://openalex.org/W2157803413, https://openalex.org/W2339209549, https://openalex.org/W1980454843, https://openalex.org/W1028396330, https://openalex.org/W67124816, https://openalex.org/W1832114949, https://openalex.org/W1588696956, https://openalex.org/W1525669465, https://openalex.org/W2028052603, https://openalex.org/W2066992267, https://openalex.org/W1531147551, https://openalex.org/W1956240944, https://openalex.org/W1565991260, https://openalex.org/W2001924419, https://openalex.org/W2735118224, https://openalex.org/W2098033180, https://openalex.org/W2885978066, https://openalex.org/W138413187 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2021 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:uknowledge.uky.edu:cs_facpub-1017 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306402622 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | False |
| 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 | UKnowledge (University of Kentucky) |
| best_oa_location.source.host_organization | https://openalex.org/I143302722 |
| best_oa_location.source.host_organization_name | University of Kentucky |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I143302722 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://uknowledge.uky.edu/cs_facpub/18 |
| 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 | Computer Science Faculty Publications |
| best_oa_location.landing_page_url | https://uknowledge.uky.edu/cs_facpub/18 |
| primary_location.id | pmh:oai:uknowledge.uky.edu:cs_facpub-1017 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306402622 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | UKnowledge (University of Kentucky) |
| primary_location.source.host_organization | https://openalex.org/I143302722 |
| primary_location.source.host_organization_name | University of Kentucky |
| primary_location.source.host_organization_lineage | https://openalex.org/I143302722 |
| primary_location.license | |
| primary_location.pdf_url | https://uknowledge.uky.edu/cs_facpub/18 |
| 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 | Computer Science Faculty Publications |
| primary_location.landing_page_url | https://uknowledge.uky.edu/cs_facpub/18 |
| publication_date | 2018-01-01 |
| publication_year | 2018 |
| referenced_works | https://openalex.org/W2009408698, https://openalex.org/W3103583670, https://openalex.org/W2175223733, https://openalex.org/W2484581819, https://openalex.org/W2394669110, https://openalex.org/W2282821441, https://openalex.org/W2963149119, https://openalex.org/W3037628460, https://openalex.org/W1902237438, https://openalex.org/W2795530988 |
| referenced_works_count | 10 |
| abstract_inverted_index.A | 127 |
| abstract_inverted_index.a | 46, 65, 78, 89, 95, 114 |
| abstract_inverted_index.AI | 49 |
| abstract_inverted_index.In | 60 |
| abstract_inverted_index.We | 93, 144 |
| abstract_inverted_index.an | 74, 138 |
| abstract_inverted_index.be | 17, 26, 53, 106 |
| abstract_inverted_index.by | 45, 88 |
| abstract_inverted_index.if | 28 |
| abstract_inverted_index.in | 77 |
| abstract_inverted_index.is | 43 |
| abstract_inverted_index.it | 51 |
| abstract_inverted_index.of | 82 |
| abstract_inverted_index.or | 13 |
| abstract_inverted_index.to | 34, 55, 108 |
| abstract_inverted_index.we | 63 |
| abstract_inverted_index.AI. | 92 |
| abstract_inverted_index.NPC | 30, 41 |
| abstract_inverted_index.and | 8, 38, 99, 112 |
| abstract_inverted_index.any | 119 |
| abstract_inverted_index.are | 86 |
| abstract_inverted_index.box | 48, 91 |
| abstract_inverted_index.can | 16, 25, 52, 105 |
| abstract_inverted_index.for | 118, 137 |
| abstract_inverted_index.has | 31 |
| abstract_inverted_index.how | 83, 149 |
| abstract_inverted_index.its | 36 |
| abstract_inverted_index.our | 132 |
| abstract_inverted_index.the | 29, 32, 57, 84, 141 |
| abstract_inverted_index.Many | 0 |
| abstract_inverted_index.NPCs | 15 |
| abstract_inverted_index.When | 40 |
| abstract_inverted_index.data | 97, 111 |
| abstract_inverted_index.game | 79 |
| abstract_inverted_index.hard | 54 |
| abstract_inverted_index.made | 87 |
| abstract_inverted_index.that | 67, 104, 131 |
| abstract_inverted_index.they | 20 |
| abstract_inverted_index.this | 61 |
| abstract_inverted_index.turn | 122 |
| abstract_inverted_index.used | 107 |
| abstract_inverted_index.when | 19 |
| abstract_inverted_index.with | 12, 146 |
| abstract_inverted_index.(NPC) | 6 |
| abstract_inverted_index.These | 23 |
| abstract_inverted_index.about | 148 |
| abstract_inverted_index.agent | 139 |
| abstract_inverted_index.based | 123 |
| abstract_inverted_index.black | 47, 90 |
| abstract_inverted_index.game, | 142 |
| abstract_inverted_index.games | 2 |
| abstract_inverted_index.model | 117 |
| abstract_inverted_index.shows | 130 |
| abstract_inverted_index.study | 129 |
| abstract_inverted_index.task. | 126 |
| abstract_inverted_index.train | 113 |
| abstract_inverted_index.gather | 109 |
| abstract_inverted_index.making | 125 |
| abstract_inverted_index.neural | 100 |
| abstract_inverted_index.paper, | 62 |
| abstract_inverted_index.people | 150 |
| abstract_inverted_index.robust | 96 |
| abstract_inverted_index.system | 50, 66 |
| abstract_inverted_index.ability | 33 |
| abstract_inverted_index.actions | 37, 76 |
| abstract_inverted_index.against | 14 |
| abstract_inverted_index.agent's | 75 |
| abstract_inverted_index.avoided | 27 |
| abstract_inverted_index.explain | 35 |
| abstract_inverted_index.feature | 3 |
| abstract_inverted_index.natural | 70 |
| abstract_inverted_index.network | 101 |
| abstract_inverted_index.outline | 94 |
| abstract_inverted_index.perform | 21 |
| abstract_inverted_index.playing | 11, 140 |
| abstract_inverted_index.present | 64 |
| abstract_inverted_index.similar | 120 |
| abstract_inverted_index.Frogger. | 143 |
| abstract_inverted_index.behavior | 42 |
| abstract_inverted_index.computer | 1 |
| abstract_inverted_index.conclude | 145 |
| abstract_inverted_index.decision | 124 |
| abstract_inverted_index.generate | 56 |
| abstract_inverted_index.however, | 10 |
| abstract_inverted_index.insights | 147 |
| abstract_inverted_index.language | 71 |
| abstract_inverted_index.perceive | 151 |
| abstract_inverted_index.pipeline | 103 |
| abstract_inverted_index.produces | 134 |
| abstract_inverted_index.training | 102 |
| abstract_inverted_index.decisions | 85 |
| abstract_inverted_index.generated | 153 |
| abstract_inverted_index.generates | 68 |
| abstract_inverted_index.necessary | 58 |
| abstract_inverted_index.rationale | 115 |
| abstract_inverted_index.teammates | 7 |
| abstract_inverted_index.technique | 133 |
| abstract_inverted_index.believable | 135 |
| abstract_inverted_index.charactert | 5 |
| abstract_inverted_index.collection | 98 |
| abstract_inverted_index.controlled | 44 |
| abstract_inverted_index.generation | 116 |
| abstract_inverted_index.non-player | 4 |
| abstract_inverted_index.rationales | 136 |
| abstract_inverted_index.regardless | 81 |
| abstract_inverted_index.sequential | 121 |
| abstract_inverted_index.companions; | 9 |
| abstract_inverted_index.environment | 80 |
| abstract_inverted_index.frustrating | 18 |
| abstract_inverted_index.human-like, | 69 |
| abstract_inverted_index.rationales. | 154 |
| abstract_inverted_index.think-aloud | 110 |
| abstract_inverted_index.frustrations | 24 |
| abstract_inverted_index.motivations. | 39 |
| abstract_inverted_index.automatically | 152 |
| abstract_inverted_index.explanations. | 59 |
| abstract_inverted_index.human-subject | 128 |
| abstract_inverted_index.unexpectedly. | 22 |
| abstract_inverted_index.rationales—of | 73 |
| abstract_inverted_index.explanations—called | 72 |
| cited_by_percentile_year.max | 94 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.5099999904632568 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.62392473 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |