{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T22:08:46Z","timestamp":1782252526509,"version":"3.54.5"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tai.2022.3223892","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T15:04:13Z","timestamp":1669302253000},"page":"1443-1457","source":"Crossref","is-referenced-by-count":16,"title":["Explain the Explainer: Interpreting Model-Agnostic Counterfactual Explanations of a Deep Reinforcement Learning Agent"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2585-637X","authenticated-orcid":false,"given":"Ziheng","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7669-9055","authenticated-orcid":false,"given":"Fabrizio","family":"Silvestri","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering and the Department of Computer Science, Sapienza University of Rome, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7471-6659","authenticated-orcid":false,"given":"Gabriele","family":"Tolomei","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering and the Department of Computer Science, Sapienza University of Rome, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3165-7051","authenticated-orcid":false,"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Intelligent Science, Xi'an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rutgers University–New Brunswick, Piscataway, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8924-6159","authenticated-orcid":false,"given":"Hongshik","family":"Ahn","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Regulation (EU) 2016\/679 of the European parliament (GDPR)","volume-title":"Official J. Eur. Union","volume":"L119","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3435104"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3233547.3233667"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6"},{"key":"ref5","article-title":"Local rule-based explanations of black box decision systems","author":"Guidotti","year":"2018"},{"key":"ref6","article-title":"Counterfactual explanations for machine learning: A review","author":"Verma","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/395"},{"key":"ref9","first-page":"265","article-title":"Algorithmic recourse under imperfect causal knowledge: A probabilistic approach","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Karimi","year":"2020"},{"key":"ref10","first-page":"895","article-title":"Model-agnostic counterfactual explanations for consequential decisions","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"108","author":"Karimi","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287569"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287566"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3063289"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380087"},{"key":"ref15","article-title":"Interpretable credit application predictions with counterfactual explanations","author":"McGrath","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86520-7_40"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58112-1_31"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403066"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098039"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20468"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref22","first-page":"4499","article-title":"CF-GNNExplainer: Counterfactual explanations for graph neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"151","author":"Lucic","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372850"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10226"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11527862_14"},{"key":"ref26","first-page":"36","article-title":"Half field offense: An environment for multiagent learning and ad hoc teamwork","volume-title":"Proc. AAMAS Adaptive Learn. Agents Workshop","author":"Hausknecht","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2017.33"},{"key":"ref28","first-page":"358","article-title":"Hierarchical approaches for reinforcement learning in parameterized action space","volume-title":"Proc. AAAI Spring Symp. Ser.","author":"Wei","year":"2018"},{"key":"ref29","article-title":"Parametrized deep Q-networks learning: Reinforcement learning with discrete-continuous hybrid action space","author":"Xiong","year":"2018"},{"key":"ref30","first-page":"1","article-title":"Playing atari with deep reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Deep Learn. Workshop","author":"Mnih","year":"2013"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref32","first-page":"5052","article-title":"Programmatically interpretable reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma","year":"2018"},{"key":"ref33","first-page":"15726","article-title":"Imitation-projected programmatic reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Verma","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314638"},{"key":"ref35","article-title":"Distilling a neural network into a soft decision tree","volume-title":"Proc. Workshop Comprehensibility Explanation AI ML","volume":"2071","author":"Frosst","year":"2017"},{"key":"ref36","first-page":"2499","article-title":"Verifiable reinforcement learning via policy extraction","author":"Bastani","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.022"},{"key":"ref38","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"15","author":"Ross","year":"2011"},{"key":"ref39","article-title":"Counterfactual explanations for arbitrary regression models","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop Algorithmic Recourse","author":"Spooner","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2945326"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref42","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref43","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Hu","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.33"},{"key":"ref45","article-title":"Exploration by random network distillation","author":"Burda","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00642"},{"key":"ref48","article-title":"Breast cancer dataset","year":"1995"},{"key":"ref49","article-title":"Credit card fraud","year":"2022"},{"key":"ref50","article-title":"Diabetes dataset","year":"1988"},{"key":"ref51","article-title":"Dataset sonar","year":"1988"},{"key":"ref52","article-title":"Wave dataset","year":"1988"},{"key":"ref53","article-title":"Boston housing dataset","year":"1978"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0086637"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa050080"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0241332"},{"key":"ref57","volume-title":"Current World Population","year":"2013"},{"key":"ref58","volume-title":"The CIA World Factbook 2020","year":"2020"},{"key":"ref59","volume-title":"Global Health Workforce Statistics","year":"2020"},{"key":"ref60","volume-title":"Prevalence of Obesity Among Adults","year":"2017"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10495741\/09960739.pdf?arnumber=9960739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:24Z","timestamp":1755911364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9960739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":60,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3223892","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}