{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T06:07:37Z","timestamp":1790662057052,"version":"4.1.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031020551","type":"print"},{"value":"9783031020568","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-02056-8_18","type":"book-chapter","created":{"date-parts":[[2022,4,19]],"date-time":"2022-04-19T06:03:00Z","timestamp":1650348180000},"page":"278-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Multi-objective Genetic Programming for\u00a0Explainable Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Mathurin","family":"Videau","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Leite","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Teytaud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Schoenauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,4,13]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: ICML, p. 1 (2004)","DOI":"10.1145\/1015330.1015430"},{"issue":"5","key":"18_CR2","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469\u2013483 (2009)","journal-title":"Robot. Auton. Syst."},{"key":"18_CR3","first-page":"82","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. IF 58, 82\u2013115 (2020)","journal-title":"IF"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Auger, A., Schoenauer, M., Teytaud, O.: Local and global order 3\/2 convergence of a surrogate evolutionary algorithm. In: GECCO, p. 8 (2005)","DOI":"10.1145\/1068009.1068154"},{"key":"18_CR5","unstructured":"Bastani, O., Pu, Y., Solar-Lezama, A.: Verifiable reinforcement learning via policy extraction. arXiv:1805.08328 (2018)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Beyer, H.G., Hellwig, M.: Controlling population size and mutation strength by meta-ES under fitness noise. In: FOGA, pp. 11\u201324 (2013)","DOI":"10.1145\/2460239.2460242"},{"key":"18_CR7","doi-asserted-by":"publisher","DOI":"10.1201\/9780429027192","volume-title":"Explanatory Model Analysis: Explore, Explain And Examine Predictive Models","author":"P Biecek","year":"2021","unstructured":"Biecek, P., Burzykowski, T.: Explanatory Model Analysis: Explore, Explain And Examine Predictive Models. CRC Press, Boca Raton (2021)"},{"key":"18_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-31030-5","volume-title":"Linear Genetic Programming","author":"MF Brameier","year":"2007","unstructured":"Brameier, M.F., Banzhaf, W.: Linear Genetic Programming. Springer, Cham (2007). https:\/\/doi.org\/10.1007\/978-0-387-31030-5"},{"key":"18_CR9","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv:1606.01540 (2016)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Cazenave, T.: Nested Monte-Carlo search. In: IJCAI (2009)","DOI":"10.1109\/IPDPS.2009.5161122"},{"key":"18_CR11","unstructured":"Cazenille, L.: QDpy: a python framework for quality-diversity (2018). bit.ly\/3s0uyVv"},{"key":"18_CR12","unstructured":"Coppens, Y., Efthymiadis, K., Lenaerts, T., Now\u00e9, A., Miller, T., Weber, R., Magazzeni, D.: Distilling deep reinforcement learning policies in soft decision trees. In: CEX Workshop, pp. 1\u20136 (2019)"},{"key":"18_CR13","unstructured":"Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv:1702.08608 (2017)"},{"key":"18_CR14","first-page":"503","volume":"6","author":"D Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. JMLR 6, 503\u2013556 (2005)","journal-title":"JMLR"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Flageat, M., Cully, A.: Fast and stable map-elites in noisy domains using deep grids. In: ALIFE, pp. 273\u2013282 (2020)","DOI":"10.1162\/isal_a_00316"},{"key":"18_CR16","first-page":"2171","volume":"13","author":"FA Fortin","year":"2012","unstructured":"Fortin, F.A., De Rainville, F.M., Gardner, M.A., Parizeau, M., Gagn\u00e9, C.: DEAP: evolutionary algorithms made easy. JMLR 13, 2171\u20132175 (2012)","journal-title":"JMLR"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Gaier, A., Asteroth, A., Mouret, J.B.: Data-efficient exploration, optimization, and modeling of diverse designs through surrogate-assisted illumination. In: GECCO, pp. 99\u2013106 (2017)","DOI":"10.1145\/3071178.3071282"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Gilpin, L., Bau, D., Yuan, B., Bajwa, A., Specter, M., Kagal, L.: Explaining explanations: an approach to evaluating interpretability of ML. arXiv:1806.00069 (2018)","DOI":"10.1109\/DSAA.2018.00018"},{"key":"18_CR19","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: ICML, pp. 1861\u20131870 (2018)"},{"issue":"1","key":"18_CR20","first-page":"1","volume":"11","author":"N Hansen","year":"2003","unstructured":"Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. ECO 11(1), 1\u201310 (2003)","journal-title":"ECO"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Hein, D., et al.: A benchmark environment motivated by industrial control problems. In: IEEE SSCI, pp. 1\u20138 (2017)","DOI":"10.1109\/SSCI.2017.8280935"},{"key":"18_CR22","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.engappai.2018.09.007","volume":"76","author":"D Hein","year":"2018","unstructured":"Hein, D., Udluft, S., Runkler, T.A.: Interpretable policies for reinforcement learning by genetic programming. Eng. App. Artif. Intell. 76, 158\u2013169 (2018)","journal-title":"Eng. App. Artif. Intell."},{"key":"18_CR23","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. JAIR 4, 237\u2013285 (1996)","journal-title":"JAIR"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Kelly, S., Heywood, M.I.: Multi-task learning in Atari video games with emergent tangled program graphs. In: GECCO, pp. 195\u2013202 (2017)","DOI":"10.1145\/3071178.3071303"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: IJCNN, pp. 1942\u20131948 (1995)","DOI":"10.1109\/ICNN.1995.488968"},{"key":"18_CR26","volume-title":"Genetic Programming: On the Programming of Computers by means of Natural Evolution","author":"JR Koza","year":"1992","unstructured":"Koza, J.R.: Genetic Programming: On the Programming of Computers by means of Natural Evolution. MIT Press, Massachusetts (1992)"},{"key":"18_CR27","unstructured":"Kubal\u00edk, J., \u017degklitz, J., Derner, E., Babu\u0161ka, R.: Symbolic regression methods for reinforcement learning. arXiv:1903.09688 (2019)"},{"key":"18_CR28","unstructured":"Kwee, I., Hutter, M., Schmidhuber, J.: Gradient-based reinforcement planning in policy-search methods. In: Wiering, M.A. (ed.) EWRL. vol. 27, pp. 27\u201329 (2001)"},{"key":"18_CR29","unstructured":"Landajuela, M., et al.: Discovering symbolic policies with deep reinforcement learning. In: ICML, pp. 5979\u20135989 (2021)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Liu, G., Schulte, O., Zhu, W., Li, Q.: Toward interpretable deep reinforcement learning with linear model u-trees. In: ECML PKDD, pp. 414\u2013429 (2018)","DOI":"10.1007\/978-3-030-10928-8_25"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Liventsev, V., H\u00e4rm\u00e4, A., Petkovi\u0107, M.: Neurogenetic programming framework for explainable reinforcement learning. arXiv:2102.04231 (2021)","DOI":"10.1145\/3449726.3459537"},{"key":"18_CR32","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: NeurIPS, pp. 4768\u20134777 (2017)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Maes, F., Fonteneau, R., Wehenkel, L., Ernst, D.: Policy search in a space of simple closed-form formulas: towards interpretability of reinforcement learning. In: ICDS, pp. 37\u201351 (2012)","DOI":"10.1007\/978-3-642-33492-4_6"},{"key":"18_CR34","unstructured":"Mania, H., Guy, A., Recht, B.: Simple random search provides a competitive approach to reinforcement learning. arXiv:1803.07055 (2018)"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Meunier, L., et al.: Black-box optimization revisited: Improving algorithm selection wizards through massive benchmarking. In: IEEE TEVC (2021)","DOI":"10.1109\/TEVC.2021.3108185"},{"key":"18_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019)","journal-title":"Artif. Intell."},{"key":"18_CR37","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML, pp. 1928\u20131937 (2016)"},{"key":"18_CR38","unstructured":"Mouret, J.B., Clune, J.: Illuminating search spaces by mapping elites. arXiv:1504.04909 (2015)"},{"key":"18_CR39","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3389\/frobt.2016.00040","volume":"3","author":"JK Pugh","year":"2016","unstructured":"Pugh, J.K., Soros, L.B., Stanley, K.O.: Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI 3, 40 (2016)","journal-title":"Front. Robot. AI"},{"key":"18_CR40","unstructured":"Rapin, J., Teytaud, O.: Nevergrad - a gradient-free optimization platform (2018). bit.ly\/3g8wghU"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you? Explaining the predictions of any classifier. In: SIGKDD, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"18_CR42","unstructured":"Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: AISTATS, pp. 627\u2013635 (2011)"},{"key":"18_CR43","unstructured":"Roth, A.M., Topin, N., Jamshidi, P., Veloso, M.: Conservative q-improvement: reinforcement learning for an interpretable decision-tree policy. arXiv:1907.01180 (2019)"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Russell, S.: Learning agents for uncertain environments. In: COLT, pp. 101\u2013103 (1998)","DOI":"10.1145\/279943.279964"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Schoenauer, M., Ronald, E.: Neuro-genetic truck backer-upper controller. In: IEEE CEC, pp. 720\u2013723 (1994)","DOI":"10.1109\/ICEC.1994.349969"},{"key":"18_CR46","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., et al.: Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"18_CR48","unstructured":"Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: ICML, pp. 3145\u20133153 (2017)"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Sigaud, O., Stulp, F.: Policy search in continuous action domains: an overview. arXiv:1803.04706 (2018)","DOI":"10.1016\/j.neunet.2019.01.011"},{"issue":"4","key":"18_CR50","first-page":"341","volume":"11","author":"R Storn","year":"1997","unstructured":"Storn, R., Price, K.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. JGO 11(4), 341\u2013359 (1997)","journal-title":"JGO"},{"key":"18_CR51","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT press, Cambridge (2018)","edition":"2"},{"key":"18_CR52","unstructured":"Verma, A., Murali, V., Singh, R., Kohli, P., Chaudhuri, S.: Programmatically interpretable reinforcement learning. In: ICML, pp. 5045\u20135054 (2018)"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Wilson, D.G., Cussat-Blanc, S., Luga, H., Miller, J.F.: Evolving simple programs for playing Atari games. In: GECCO, pp. 229\u2013236 (2018)","DOI":"10.1145\/3205455.3205578"},{"issue":"3","key":"18_CR54","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1007\/s40747-020-00175-y","volume":"6","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Zhou, A., Lin, X.: Interpretable policy derivation for reinforcement learning based on evolutionary feature synthesis. Complex Intell. Syst. 6(3), 741\u2013753 (2020). https:\/\/doi.org\/10.1007\/s40747-020-00175-y","journal-title":"Complex Intell. Syst."}],"container-title":["Lecture Notes in Computer Science","Genetic Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-02056-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T08:50:42Z","timestamp":1726995042000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-02056-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031020551","9783031020568"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-02056-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"13 April 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EuroGP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Genetic Programming (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 April 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 April 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eurogp2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.evostar.org\/2022\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","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":"12","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":"7","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":"34% - 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":"4","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":"3","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)"}}]}}