{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:43Z","timestamp":1740108043071,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Gorilla Experiment Builder"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s00521-023-08696-6","type":"journal-article","created":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T08:02:23Z","timestamp":1689667343000},"page":"505-516","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparing explanations in RL"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-5386","authenticated-orcid":false,"given":"Britt Davis","family":"Pierson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dustin","family":"Arendt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Miller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"8696_CR1","doi-asserted-by":"publisher","unstructured":"Alqaraawi A, Schuessler M, Wei\u00df P, et al (2020) Evaluating saliency map explanations for convolutional neural networks: a user study. In: Proceedings of the 25th international conference on intelligent user interfaces. ACM, pp 275\u2013285, https:\/\/doi.org\/10.1145\/3377325.3377519","DOI":"10.1145\/3377325.3377519"},{"key":"8696_CR2","unstructured":"Amir D, Amir O (2018) HIGHLIGHTS: summarizing agent behavior to people. In: Proceedings of the international conference on autonomous agents and multiagent systems 17:9"},{"issue":"5","key":"8696_CR3","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/s10458-019-09418-","volume":"33","author":"O Amir","year":"2019","unstructured":"Amir O, Doshi-Velez F, Sarne D (2019) Summarizing agent strategies. Autonom Agents Multi-Agent Syst 33(5):628\u2013644. https:\/\/doi.org\/10.1007\/s10458-019-09418-","journal-title":"Autonom Agents Multi-Agent Syst"},{"issue":"2","key":"8696_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3366485","volume":"10","author":"A Anderson","year":"2020","unstructured":"Anderson A, Dodge J, Sadarangani A et al (2020) Mental models of mere mortals with explanations of reinforcement learning. ACM Trans Inter Int Syst 10(2):1\u201337. https:\/\/doi.org\/10.1145\/3366485","journal-title":"ACM Trans Inter Int Syst"},{"key":"8696_CR5","unstructured":"Bogdanovic M, Markovikj D, Denil M, et al (2015) Deep apprenticeship learning for playing video games. In: Workshops at the AAAI conference on artificial intelligence"},{"key":"8696_CR6","unstructured":"Brockman G, Cheung V, Pettersson L, et al (2016) OpenAI Gym. arXiv:1606.01540"},{"key":"8696_CR7","unstructured":"Brown A, Petrik M (2018) Interpretable reinforcement learning with ensemble methods. arXiv:1809.06995"},{"issue":"4","key":"8696_CR8","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1111\/j.1745-3984.1993.tb00427.x","volume":"30","author":"D Budescu","year":"1993","unstructured":"Budescu D, Bar-Hillel M (1993) To guess or not to guess: a decision-theoretic view of formula scoring. J Edu Meas 30(4):277\u2013291. https:\/\/doi.org\/10.1111\/j.1745-3984.1993.tb00427.x","journal-title":"J Edu Meas"},{"key":"8696_CR9","doi-asserted-by":"publisher","unstructured":"Cer D, Yang Y, yi Kong S, et al (2018) Universal sentence encoder for english. In: Proceedings of the 2018 conference on empirical methods in natural language processing: system demonstrations. Association for computational linguistics, https:\/\/doi.org\/10.18653\/v1\/d18-2029","DOI":"10.18653\/v1\/d18-2029"},{"key":"8696_CR10","doi-asserted-by":"publisher","unstructured":"Chatzimparmpas A, Martins RM, Jusufi I, et al (2020) The state of the art in enhancing trust in machine learning models with the use of visualizations. In: Computer Graphics Forum, vol 39. Wiley, pp 713\u2013756, https:\/\/doi.org\/10.1111\/cgf.14034","DOI":"10.1111\/cgf.14034"},{"key":"8696_CR11","doi-asserted-by":"crossref","unstructured":"Cideron G, Seurin M, Strub F, et al (2020) HIGhER : improving instruction following with hindsight generation for experience replay. arXiv:1910.09451","DOI":"10.1109\/SSCI47803.2020.9308603"},{"key":"8696_CR12","doi-asserted-by":"crossref","unstructured":"Davis B, Glenski M, Sealy W, et al (2020) Measure utility, gain trust: practical advice for XAI researchers. arXiv:2009.12924","DOI":"10.1109\/TREX51495.2020.00005"},{"key":"8696_CR13","unstructured":"Ellis R, McClintock A (1994) Communication model. In: If you take my meaning: theory into practice in human communication, 2nd edn. E. Arnold : distributed in the USA by Routledge, Chapman and Hall, London ; New York, p 71"},{"issue":"1","key":"8696_CR14","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.ijhcs.2008.09.008","volume":"67","author":"SR Haynes","year":"2009","unstructured":"Haynes SR, Cohen MA, Ritter FE (2009) Designs for explaining intelligent agents. Int J Human-Comput Stud 67(1):90\u2013110. https:\/\/doi.org\/10.1016\/j.ijhcs.2008.09.008","journal-title":"Int J Human-Comput Stud"},{"key":"8696_CR15","unstructured":"Heaven WD (2020) Why asking an ai to explain itself can make things worse. MIT Technology Review"},{"key":"8696_CR16","unstructured":"Huber T (2020) HIGHLIGHTS-LRP. https:\/\/github.com\/HuTobias\/HIGHLIGHTS-LRP"},{"key":"8696_CR17","doi-asserted-by":"crossref","unstructured":"Huber T, Weitz K, Andr\u00e9 E, et al (2020) Local and global explanations of agent behavior: integrating strategy summaries with saliency maps. arXiv:2005.08874","DOI":"10.1016\/j.artint.2021.103571"},{"key":"8696_CR18","unstructured":"Juozapaitis Z, Koul A, Fern A, et al (2019) Explainable reinforcement learning via reward decomposition. In: Proceedings at the international joint conference on artificial intelligence. A workshop on explainable artificial intelligence"},{"key":"8696_CR19","doi-asserted-by":"publisher","unstructured":"Kawano H (2013) Hierarchical aub-task decomposition for reinforcement learning of multi-robot delivery mission. In: 2013 IEEE international conference on robotics and automation. IEEE, pp 828\u2013835, https:\/\/doi.org\/10.1109\/ICRA.2013.6630669","DOI":"10.1109\/ICRA.2013.6630669"},{"key":"8696_CR20","doi-asserted-by":"crossref","unstructured":"Liu X, Wang X, Matwin S (2018) Interpretable deep convolutional neural networks via meta-learning. arXiv:1802.00560","DOI":"10.1109\/IJCNN.2018.8489172"},{"key":"8696_CR21","doi-asserted-by":"crossref","unstructured":"Madumal P, Miller T, Sonenberg L, et al (2019) Explainable reinforcement learning through a causal lens. arXiv:1905.10958","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"8696_CR22","unstructured":"Madumal P, Miller T, Sonenberg L, et al (2020) Distal explanations for model-free explainable reinforcement learning. arxiv:2001.10284"},{"issue":"7540","key":"8696_CR23","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"8696_CR24","unstructured":"Pierson BD, Ventura J, Taylor ME (2021) The atari data scraper. arXiv:2104.04893"},{"key":"8696_CR25","unstructured":"Roth AM, Topin N, Jamshidi P, et al (2019) Conservative Q-improvement: reinforcement learning for an interpretable decision-tree policy. arXiv:1907.01180"},{"key":"8696_CR26","unstructured":"Russell S, Zimdars AL (2003) Q-decomposition for reinforcement learning agents. In: Proceedings of the twentieth international conference on international conference on machine learning. AAAI Press, ICML\u201903, p 656-663"},{"key":"8696_CR27","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.cogsys.2017.02.002","volume":"46","author":"KE Schaefer","year":"2017","unstructured":"Schaefer KE, Straub ER, Chen JY et al (2017) Communicating intent to develop shared situation awareness and engender trust in human-agent teams. Cogn Syst Res 46:26\u201339. https:\/\/doi.org\/10.1016\/j.cogsys.2017.02.002","journal-title":"Cogn Syst Res"},{"key":"8696_CR28","unstructured":"van Seijen H, Fatemi M, Romoff J, et al (2017) Hybrid reward architecture for reinforcement learning. arXiv:1706.04208"},{"issue":"103","key":"8696_CR29","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/j.artint.2020.103367","volume":"288","author":"P Sequeira","year":"2020","unstructured":"Sequeira P, Gervasio M (2020) Interestingness elements for explainable reinforcement learning: understanding agents\u2019 capabilities and limitations. Artif Intell 288(103):367. https:\/\/doi.org\/10.1016\/j.artint.2020.103367","journal-title":"Artif Intell"},{"key":"8696_CR30","unstructured":"Wang Z, Schaul T, Hessel M, et al (2016) Dueling network architectures for deep reinforcement learning. arXiv:1511.06581"},{"key":"8696_CR31","doi-asserted-by":"publisher","unstructured":"Yang F, Huang Z, Scholtz J, et al (2020) How do visual explanations foster end users\u2019 appropriate trust in machine learning? In: Proceedings of the 25th international conference on intelligent user interfaces. ACM, pp 189\u2013201, https:\/\/doi.org\/10.1145\/3377325.3377480","DOI":"10.1145\/3377325.3377480"},{"key":"8696_CR32","doi-asserted-by":"publisher","unstructured":"Yin M, Wortman Vaughan J, Wallach H (2019) Understanding the effect of accuracy on trust in machine learning models. In: Proceedings of the 2019 CHI conference on human factors in computing systems. ACM, pp 1\u201312, https:\/\/doi.org\/10.1145\/3290605.3300509","DOI":"10.1145\/3290605.3300509"},{"issue":"8","key":"8696_CR33","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1109\/TNNLS.2012.2200299","volume":"23","author":"SE Yuksel","year":"2012","unstructured":"Yuksel SE, Wilson JN, Gader PD (2012) Twenty years of mixture of experts. IEEE Trans Neural Netw Learn Syst 23(8):1177\u20131193. https:\/\/doi.org\/10.1109\/TNNLS.2012.2200299","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08696-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08696-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08696-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T17:07:33Z","timestamp":1704388053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08696-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["8696"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08696-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"15 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The user study design was reviewed and approved for exemption by the Washington State University IRB.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All participants in the user study gave consent to be included in this research.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}}]}}