{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:25:22Z","timestamp":1778347522590,"version":"3.51.4"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030794569","type":"print"},{"value":"9783030794576","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-79457-6_15","type":"book-chapter","created":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T23:03:07Z","timestamp":1626649387000},"page":"173-187","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Explainable Reinforcement Learning with the Tsetlin Machine"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2699-9903","authenticated-orcid":false,"given":"Saeed","family":"Rahimi Gorji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7287-030X","authenticated-orcid":false,"given":"Ole-Christoffer","family":"Granmo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4331-7537","authenticated-orcid":false,"given":"Marco","family":"Wiering","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"key":"15_CR1","unstructured":"Abeyrathna, K.D., et al..: Massively parallel and asynchronous Tsetlin Machine architecture supporting almost constant-time scaling. arXiv preprint arXiv:2009.04861 (2020)"},{"key":"15_CR2","doi-asserted-by":"publisher","first-page":"20190165","DOI":"10.1098\/rsta.2019.0165","volume":"378","author":"KD Abeyrathna","year":"2019","unstructured":"Abeyrathna, K.D., Granmo, O.C., Zhang, X., Jiao, L., Goodwin, M.: The regression Tsetlin Machine - a novel approach to interpretable non-linear regression. Philos. Trans. R. Soc. A 378, 20190165 (2019)","journal-title":"Philos. Trans. R. Soc. A"},{"key":"15_CR3","unstructured":"Abeyrathna, K.D., Granmo, O.-C., Goodwin, M.: A regression Tsetlin Machine with integer weighted clauses for compact pattern representation. In: 33rd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA\/AIE 2020). Springer (2020)"},{"key":"15_CR4","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1007\/978-3-030-30244-3_23","volume-title":"Progress in Artificial Intelligence","author":"KD Abeyrathna","year":"2019","unstructured":"Abeyrathna, K.D., Granmo, O.-C., Jiao, L., Goodwin, M.: The regression Tsetlin Machine: a Tsetlin Machine for continuous output problems. In: Moura Oliveira, P., Novais, P., Reis, L.P. (eds.) EPIA 2019. LNCS (LNAI), vol. 11805, pp. 268\u2013280. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30244-3_23"},{"key":"15_CR5","doi-asserted-by":"publisher","first-page":"115134","DOI":"10.1109\/ACCESS.2019.2935416","volume":"7","author":"GT Berge","year":"2019","unstructured":"Berge, G.T., Granmo, O.C., Tveit, T.O., Goodwin, M., Jiao, L., Matheussen, B.V.: Using the Tsetlin Machine to learn human-interpretable rules for high-accuracy text categorization with medical applications. IEEE Access 7, 115134\u2013115146 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2935416","journal-title":"IEEE Access"},{"key":"15_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1007\/978-3-540-39857-8_11","volume-title":"Machine Learning: ECML 2003","author":"D Ernst","year":"2003","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Iteratively extending time horizon reinforcement learning. In: Lavra\u010d, N., Gamberger, D., Blockeel, H., Todorovski, L. (eds.) ECML 2003. LNCS (LNAI), vol. 2837, pp. 96\u2013107. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-39857-8_11"},{"key":"15_CR7","first-page":"503","volume":"6","author":"D Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. J. Mach. Learn. Res. 6, 503\u2013556 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR8","doi-asserted-by":"publisher","unstructured":"Ernst, D., Glavic, M., Geurts, P., Wehenkel, L.: Approximate value iteration in the reinforcement learning context. Application to electrical power system control. Int. J. Emerg. Electr. Power Syst. 3 (2005). https:\/\/doi.org\/10.2202\/1553-779X.1066","DOI":"10.2202\/1553-779X.1066"},{"key":"15_CR9","unstructured":"Granmo, O.C.: The Tsetlin Machine - a game theoretic bandit driven approach to optimal pattern recognition with propositional logic. arXiv preprint arXiv:1804.01508 (2018)"},{"key":"15_CR10","unstructured":"Granmo, O.C., Glimsdal, S., Jiao, L., Goodwin, M., Omlin, C.W., Berge, G.T.: The convolutional Tsetlin Machine. arXiv preprint, arXiv:1905.09688 (2019)"},{"key":"15_CR11","unstructured":"Phoulady, A., Granmo, O.C., Rahimi Gorji, S., Phoulady, H.A.: The weighted tsetlin machine: compressed representations with clause weighting. In: Ninth International Workshop on Statistical Relational AI (StarAI 2020) (2020)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Puterman, M.L., Shin, M.C.: Modified policy iteration algorithms for discounted Markov decision problems. Manag. Sci. 24(11), 1127\u20131137 (1978). http:\/\/www.jstor.org\/stable\/2630487","DOI":"10.1287\/mnsc.24.11.1127"},{"key":"15_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-030-55789-8_60","volume-title":"Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices","author":"S Rahimi Gorji","year":"2020","unstructured":"Rahimi Gorji, S., Granmo, O.-C., Glimsdal, S., Edwards, J., Goodwin, M.: Increasing the inference and learning speed of Tsetlin Machines with clause indexing. In: Fujita, H., Fournier-Viger, P., Ali, M., Sasaki, J. (eds.) IEA\/AIE 2020. LNCS (LNAI), vol. 12144, pp. 695\u2013708. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-55789-8_60"},{"key":"15_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/978-3-030-34885-4_11","volume-title":"Artificial Intelligence XXXVI","author":"S Rahimi Gorji","year":"2019","unstructured":"Rahimi Gorji, S., Granmo, O.-C., Phoulady, A., Goodwin, M.: A Tsetlin Machine with multigranular clauses. In: Bramer, M., Petridis, M. (eds.) SGAI 2019. LNCS (LNAI), vol. 11927, pp. 146\u2013151. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-34885-4_11"},{"key":"15_CR15","unstructured":"Rosenstein, M., Barto, A.: Supervised learning combined with an actor-critic architecture title2: Tech. rep., USA (2002)"},{"key":"15_CR16","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"issue":"11","key":"15_CR17","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1145\/1968.1972","volume":"27","author":"LG Valiant","year":"1984","unstructured":"Valiant, L.G.: A theory of the learnable. Commun. ACM 27(11), 1134\u20131142 (1984). https:\/\/doi.org\/10.1145\/1968.1972","journal-title":"Commun. ACM"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, X., Jiao, L., Granmo, O.C., Goodwin, M.: On the convergence of Tsetlin Machines for the identity-and not operators. arXiv preprint arXiv:2007.14268 (2020)","DOI":"10.1109\/TPAMI.2021.3085591"}],"container-title":["Lecture Notes in Computer Science","Advances and Trends in Artificial Intelligence. Artificial Intelligence Practices"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-79457-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T23:07:31Z","timestamp":1626649651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-79457-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030794569","9783030794576"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-79457-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"19 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IEA\/AIE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kuala Lumpur","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malaysia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ieaaie2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieeecomputer.my\/ieaaie2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"145","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"87","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"19","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"60% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.35","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}