Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning Article Swipe
Tongzhou Mu
,
Kaixiang Lin
,
Feiyang Niu
,
Govind Thattai
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2201.08520
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2201.08520
We present a two-step hybrid reinforcement learning (RL) policy that is designed to generate interpretable and robust hierarchical policies on the RL problem with graph-based input. Unlike prior deep reinforcement learning policies parameterized by an end-to-end black-box graph neural network, our approach disentangles the decision-making process into two steps. The first step is a simplified classification problem that maps the graph input to an action group where all actions share a similar semantic meaning. The second step implements a sophisticated rule-miner that conducts explicit one-hop reasoning over the graph and identifies decisive edges in the graph input without the necessity of heavy domain knowledge. This two-step hybrid policy presents human-friendly interpretations and achieves better performance in terms of generalization and robustness. Extensive experimental studies on four levels of complex text-based games have demonstrated the superiority of the proposed method compared to the state-of-the-art.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2201.08520
- https://arxiv.org/pdf/2201.08520
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4221153266
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4221153266Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2201.08520Digital Object Identifier
- Title
-
Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-21Full publication date if available
- Authors
-
Tongzhou Mu, Kaixiang Lin, Feiyang Niu, Govind ThattaiList of authors in order
- Landing page
-
https://arxiv.org/abs/2201.08520Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2201.08520Direct 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/2201.08520Direct OA link when available
- Concepts
-
Reinforcement learning, Computer science, Artificial intelligence, Parameterized complexity, Graph, Robustness (evolution), Machine learning, Theoretical computer science, Algorithm, Biochemistry, Chemistry, GeneTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4221153266 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2201.08520 |
| ids.doi | https://doi.org/10.48550/arxiv.2201.08520 |
| ids.openalex | https://openalex.org/W4221153266 |
| fwci | |
| type | preprint |
| title | Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| 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 | 0.9695000052452087 |
| 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/T12026 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9678999781608582 |
| 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 | Explainable Artificial Intelligence (XAI) |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C97541855 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8125032186508179 |
| 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 | 0.704224705696106 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6156067848205566 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C165464430 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5857436656951904 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1570441 |
| concepts[3].display_name | Parameterized complexity |
| concepts[4].id | https://openalex.org/C132525143 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5724758505821228 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[4].display_name | Graph |
| concepts[5].id | https://openalex.org/C63479239 |
| concepts[5].level | 3 |
| concepts[5].score | 0.4714943766593933 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[5].display_name | Robustness (evolution) |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.44038230180740356 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C80444323 |
| concepts[7].level | 1 |
| concepts[7].score | 0.42470812797546387 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[7].display_name | Theoretical computer science |
| concepts[8].id | https://openalex.org/C11413529 |
| concepts[8].level | 1 |
| concepts[8].score | 0.19083723425865173 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[8].display_name | Algorithm |
| concepts[9].id | https://openalex.org/C55493867 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[9].display_name | Biochemistry |
| concepts[10].id | https://openalex.org/C185592680 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[10].display_name | Chemistry |
| concepts[11].id | https://openalex.org/C104317684 |
| concepts[11].level | 2 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[11].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/reinforcement-learning |
| keywords[0].score | 0.8125032186508179 |
| keywords[0].display_name | Reinforcement learning |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.704224705696106 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6156067848205566 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/parameterized-complexity |
| keywords[3].score | 0.5857436656951904 |
| keywords[3].display_name | Parameterized complexity |
| keywords[4].id | https://openalex.org/keywords/graph |
| keywords[4].score | 0.5724758505821228 |
| keywords[4].display_name | Graph |
| keywords[5].id | https://openalex.org/keywords/robustness |
| keywords[5].score | 0.4714943766593933 |
| keywords[5].display_name | Robustness (evolution) |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.44038230180740356 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[7].score | 0.42470812797546387 |
| keywords[7].display_name | Theoretical computer science |
| keywords[8].id | https://openalex.org/keywords/algorithm |
| keywords[8].score | 0.19083723425865173 |
| keywords[8].display_name | Algorithm |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2201.08520 |
| 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/2201.08520 |
| 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/2201.08520 |
| locations[1].id | doi:10.48550/arxiv.2201.08520 |
| 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.2201.08520 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5091792127 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4384-2526 |
| authorships[0].author.display_name | Tongzhou Mu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Mu, Tongzhou |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100443077 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-8626-8934 |
| authorships[1].author.display_name | Kaixiang Lin |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lin, Kaixiang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5058043142 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Feiyang Niu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Niu, Feiyang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5088771920 |
| authorships[3].author.orcid | https://orcid.org/0009-0005-1010-8896 |
| authorships[3].author.display_name | Govind Thattai |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Thattai, Govind |
| 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/2201.08520 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-04-03T00:00:00 |
| display_name | Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| 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 | 0.9695000052452087 |
| 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/W2051058708, https://openalex.org/W1494268238, https://openalex.org/W154868527, https://openalex.org/W1983207144, https://openalex.org/W2490706771, https://openalex.org/W2480116122, https://openalex.org/W4255576661, https://openalex.org/W1516574938, https://openalex.org/W2053685668, https://openalex.org/W2914625303 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2201.08520 |
| 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/2201.08520 |
| 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/2201.08520 |
| primary_location.id | pmh:oai:arXiv.org:2201.08520 |
| 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/2201.08520 |
| 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/2201.08520 |
| publication_date | 2022-01-21 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 2, 53, 70, 78 |
| abstract_inverted_index.RL | 21 |
| abstract_inverted_index.We | 0 |
| abstract_inverted_index.an | 34, 63 |
| abstract_inverted_index.by | 33 |
| abstract_inverted_index.in | 93, 115 |
| abstract_inverted_index.is | 10, 52 |
| abstract_inverted_index.of | 100, 117, 127, 135 |
| abstract_inverted_index.on | 19, 124 |
| abstract_inverted_index.to | 12, 62, 140 |
| abstract_inverted_index.The | 49, 74 |
| abstract_inverted_index.all | 67 |
| abstract_inverted_index.and | 15, 89, 111, 119 |
| abstract_inverted_index.our | 40 |
| abstract_inverted_index.the | 20, 43, 59, 87, 94, 98, 133, 136, 141 |
| abstract_inverted_index.two | 47 |
| abstract_inverted_index.(RL) | 7 |
| abstract_inverted_index.This | 104 |
| abstract_inverted_index.deep | 28 |
| abstract_inverted_index.four | 125 |
| abstract_inverted_index.have | 131 |
| abstract_inverted_index.into | 46 |
| abstract_inverted_index.maps | 58 |
| abstract_inverted_index.over | 86 |
| abstract_inverted_index.step | 51, 76 |
| abstract_inverted_index.that | 9, 57, 81 |
| abstract_inverted_index.with | 23 |
| abstract_inverted_index.edges | 92 |
| abstract_inverted_index.first | 50 |
| abstract_inverted_index.games | 130 |
| abstract_inverted_index.graph | 37, 60, 88, 95 |
| abstract_inverted_index.group | 65 |
| abstract_inverted_index.heavy | 101 |
| abstract_inverted_index.input | 61, 96 |
| abstract_inverted_index.prior | 27 |
| abstract_inverted_index.share | 69 |
| abstract_inverted_index.terms | 116 |
| abstract_inverted_index.where | 66 |
| abstract_inverted_index.Unlike | 26 |
| abstract_inverted_index.action | 64 |
| abstract_inverted_index.better | 113 |
| abstract_inverted_index.domain | 102 |
| abstract_inverted_index.hybrid | 4, 106 |
| abstract_inverted_index.input. | 25 |
| abstract_inverted_index.levels | 126 |
| abstract_inverted_index.method | 138 |
| abstract_inverted_index.neural | 38 |
| abstract_inverted_index.policy | 8, 107 |
| abstract_inverted_index.robust | 16 |
| abstract_inverted_index.second | 75 |
| abstract_inverted_index.steps. | 48 |
| abstract_inverted_index.actions | 68 |
| abstract_inverted_index.complex | 128 |
| abstract_inverted_index.one-hop | 84 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.problem | 22, 56 |
| abstract_inverted_index.process | 45 |
| abstract_inverted_index.similar | 71 |
| abstract_inverted_index.studies | 123 |
| abstract_inverted_index.without | 97 |
| abstract_inverted_index.achieves | 112 |
| abstract_inverted_index.approach | 41 |
| abstract_inverted_index.compared | 139 |
| abstract_inverted_index.conducts | 82 |
| abstract_inverted_index.decisive | 91 |
| abstract_inverted_index.designed | 11 |
| abstract_inverted_index.explicit | 83 |
| abstract_inverted_index.generate | 13 |
| abstract_inverted_index.learning | 6, 30 |
| abstract_inverted_index.meaning. | 73 |
| abstract_inverted_index.network, | 39 |
| abstract_inverted_index.policies | 18, 31 |
| abstract_inverted_index.presents | 108 |
| abstract_inverted_index.proposed | 137 |
| abstract_inverted_index.semantic | 72 |
| abstract_inverted_index.two-step | 3, 105 |
| abstract_inverted_index.Extensive | 121 |
| abstract_inverted_index.black-box | 36 |
| abstract_inverted_index.necessity | 99 |
| abstract_inverted_index.reasoning | 85 |
| abstract_inverted_index.end-to-end | 35 |
| abstract_inverted_index.identifies | 90 |
| abstract_inverted_index.implements | 77 |
| abstract_inverted_index.knowledge. | 103 |
| abstract_inverted_index.rule-miner | 80 |
| abstract_inverted_index.simplified | 54 |
| abstract_inverted_index.text-based | 129 |
| abstract_inverted_index.graph-based | 24 |
| abstract_inverted_index.performance | 114 |
| abstract_inverted_index.robustness. | 120 |
| abstract_inverted_index.superiority | 134 |
| abstract_inverted_index.demonstrated | 132 |
| abstract_inverted_index.disentangles | 42 |
| abstract_inverted_index.experimental | 122 |
| abstract_inverted_index.hierarchical | 17 |
| abstract_inverted_index.interpretable | 14 |
| abstract_inverted_index.parameterized | 32 |
| abstract_inverted_index.reinforcement | 5, 29 |
| abstract_inverted_index.sophisticated | 79 |
| abstract_inverted_index.classification | 55 |
| abstract_inverted_index.generalization | 118 |
| abstract_inverted_index.human-friendly | 109 |
| abstract_inverted_index.decision-making | 44 |
| abstract_inverted_index.interpretations | 110 |
| abstract_inverted_index.state-of-the-art. | 142 |
| 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 | 0.8199999928474426 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile |