{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:15:00Z","timestamp":1777407300997,"version":"3.51.4"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031900648","type":"print"},{"value":"9783031900655","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-90065-5_1","type":"book-chapter","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T03:08:09Z","timestamp":1745377689000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Social Interpretable Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1652-1690","authenticated-orcid":false,"given":"Leonardo Lucio","family":"Custode","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-1830","authenticated-orcid":false,"given":"Giovanni","family":"Iacca","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,17]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., Zhong, C.: Interpretable machine learning: fundamental principles and 10 grand challenges (2021). arXiv:2103.11251","DOI":"10.1214\/21-SS133"},{"key":"1_CR2","unstructured":"Kompella, V., et al.: Reinforcement learning for optimization of COVID-19 mitigation policies (2020). arXiv:2010.10560"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Custode, L.L., Iacca, G.: Interpretable AI for policy-making in pandemics. In: Genetic and Evolutionary Computation Conference Companion, pp. 1763\u20131769 (2022)","DOI":"10.1145\/3520304.3533959"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Trott, A., Srinivasa, S., van\u00a0der Wal, D., Haneuse, S., Zheng, S.: Building a foundation for data-driven, interpretable, and robust policy design using the AI economist (2021). arXiv:2108.02904","DOI":"10.2139\/ssrn.3900237"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Zheng, S., Trott, A., Srinivasa, S., Parkes, D.C., Socher, R.: The AI economist: taxation policy design via two-level deep multiagent reinforcement learning. Sci. Adv. 8(18), eabk2607 (2022)","DOI":"10.1126\/sciadv.abk2607"},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"6169","DOI":"10.1109\/ACCESS.2023.3236260","volume":"11","author":"LL Custode","year":"2023","unstructured":"Custode, L.L., Iacca, G.: Evolutionary learning of interpretable decision trees. IEEE Access 11, 6169\u20136184 (2023)","journal-title":"IEEE Access"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Custode, L.L., Iacca, G.: A co-evolutionary approach to interpretable reinforcement learning in environments with continuous action spaces. In: IEEE Symposium Series on Computational Intelligence (2021)","DOI":"10.1109\/SSCI50451.2021.9660048"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Custode, L.L., Iacca, G.: Interpretable pipelines with evolutionary optimized modules for reinforcement learning tasks with visual inputs. In: Genetic and Evolutionary Computation Conference Companion, pp. 224\u2013227 (2022)","DOI":"10.1145\/3520304.3528897"},{"key":"1_CR9","unstructured":"Dhebar, Y., Deb, K., Nageshrao, S., Zhu, L., Filev, D.: Interpretable-AI policies using evolutionary nonlinear decision trees for discrete action systems (2020). arXiv:2009.09521"},{"key":"1_CR10","unstructured":"Silva, A., Killian, T., Rodriguez, I.D.J., Son, S.H., Gombolay, M.: Optimization methods for interpretable differentiable decision trees in reinforcement learning. In: International Conference on Artificial Intelligence and Statistics, PMLR, pp. 1855\u20131865 (2020)"},{"key":"1_CR11","unstructured":"Peng, Z., Sun, H., Zhou, B.: Non-local policy optimization via diversity-regularized collaborative exploration. arXiv:2006.07781 (2020)"},{"key":"1_CR12","unstructured":"Khadka, S., et al.: Collaborative evolutionary reinforcement learning. In: International Conference on Machine Learning, PMLR, pp. 3341\u20133350 (2019)"},{"issue":"5","key":"1_CR13","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1002\/(SICI)1520-6505(1998)6:5<178::AID-EVAN5>3.0.CO;2-8","volume":"6","author":"R Dunbar","year":"1998","unstructured":"Dunbar, R.: The social brain hypothesis. Evol. Anthropol. 6(5), 178\u2013190 (1998)","journal-title":"Evol. Anthropol."},{"issue":"1480","key":"1_CR14","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1098\/rstb.2006.1998","volume":"362","author":"A Whiten","year":"2007","unstructured":"Whiten, A., van Schaik, C.P.: The evolution of animal \u2018cultures\u2019 and social intelligence. Philos. Trans. R. Soc. B 362(1480), 603\u2013620 (2007)","journal-title":"Philos. Trans. R. Soc. B"},{"key":"1_CR15","unstructured":"Zentall, T.R., Galef, B.G.: Social Learning: Psychological and Biological Perspectives. Psychology Press (1988)"},{"issue":"1653","key":"1_CR16","first-page":"2869","volume":"275","author":"MM Webster","year":"2008","unstructured":"Webster, M.M., Laland, K.N.: Social learning strategies and predation risk: minnows copy only when using private information would be costly. Proc. Roy. Soc. B Biol. Sci. 275(1653), 2869\u20132876 (2008)","journal-title":"Proc. Roy. Soc. B Biol. Sci."},{"issue":"1567","key":"1_CR17","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1098\/rstb.2010.0304","volume":"366","author":"CP Van Schaik","year":"2011","unstructured":"Van Schaik, C.P., Burkart, J.M.: Social learning and evolution: the cultural intelligence hypothesis. Philos. Trans. R. Soc. 366(1567), 1008\u20131016 (2011)","journal-title":"Philos. Trans. R. Soc."},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Franz, M., Nunn, C.L.: Rapid evolution of social learning. J. Evol. Biol. 22 (2009)","DOI":"10.1111\/j.1420-9101.2009.01804.x"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Rendell, L., et al.: Why copy others? Insights from the social learning strategies tournament. Science 328(5975), pp. 208\u2013213 (2010)","DOI":"10.1126\/science.1184719"},{"issue":"6","key":"1_CR20","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1021\/acscentsci.7b00133","volume":"3","author":"BR Stockwell","year":"2017","unstructured":"Stockwell, B.R., Stockwell, M.S., Jiang, E.: Group Problem solving in class improves undergraduate learning. ACS Cent. Sci. 3(6), 614\u2013620 (2017)","journal-title":"ACS Cent. Sci."},{"issue":"1","key":"1_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1037\/pspa0000042","volume":"110","author":"DA Kalkstein","year":"2016","unstructured":"Kalkstein, D.A., Kleiman, T., Wakslak, C.J., Liberman, N., Trope, Y.: Social learning across psychological distance. J. Pers. Soc. Psychol. 110(1), 1\u201319 (2016)","journal-title":"J. Pers. Soc. Psychol."},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Pal, A., Yang, Q., Kant, K., Zhu, K., Guo, S.: Collaborative machine learning: schemes, robustness, and privacy. IEEE Trans. Neural Netw. Learn. Syst. (2022)","DOI":"10.1109\/TNNLS.2022.3169347"},{"issue":"3","key":"1_CR23","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSP.2020.2975749","volume":"37","author":"T Li","year":"2020","unstructured":"Li, T., Sahu, A.K., Talwalkar, A., Smith, V.: Federated learning: challenges, methods, and future directions. IEEE Signal Process. Mag. 37(3), 50\u201360 (2020)","journal-title":"IEEE Signal Process. Mag."},{"key":"1_CR24","unstructured":"Wang, H., Lin, S., Zhang, J.: Adaptive ensemble Q-learning: minimizing estimation bias via error feedback. In: Advances in Neural Information Processing Systems, vol. 34, pp. 24778\u201324790 (2021)"},{"key":"1_CR25","unstructured":"Chen, R.Y., Sidor, S., Abbeel, P., Schulman, J.: UCB exploration via Q-ensembles. arXiv:1706.01502 (2017)"},{"key":"1_CR26","unstructured":"Chen, X., Wang, C., Zhou, Z., Ross, K.: Randomized ensembled double Q-learning: learning fast without a model. arXiv:2101.05982 (2021)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Yaman, A., Bredeche, N., \u00c7aylak, O., Leibo, J.Z., Lee, S.W.: Meta-control of social learning strategies. PLOS Comput. Biol. 18(2), e1009882 (2022)","DOI":"10.1371\/journal.pcbi.1009882"},{"key":"1_CR28","unstructured":"Zheng, H., Wei, P., Jiang, J., Long, G., Lu, Q., Zhang, C.: Cooperative heterogeneous deep reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17455\u201317465 (2020)"},{"key":"1_CR29","unstructured":"Team, C.G.I., et\u00a0al.: Learning robust real-time cultural transmission without human data. arXiv:2203.00715 (2022)"},{"key":"1_CR30","unstructured":"Ryabinin, M., Gusev, A.: Towards crowdsourced training of large neural networks using decentralized mixture-of-experts. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 3659\u20133672 (2020)"},{"issue":"7","key":"1_CR31","doi-asserted-by":"publisher","first-page":"3236","DOI":"10.1007\/s11227-018-2375-9","volume":"74","author":"E Kijsipongse","year":"2018","unstructured":"Kijsipongse, E., Piyatumrong, A., U-ruekolan, S.: A hybrid GPU cluster and volunteer computing platform for scalable deep learning. J. Supercomput. 74(7), 3236\u20133263 (2018). https:\/\/doi.org\/10.1007\/s11227-018-2375-9","journal-title":"J. Supercomput."},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Atre, M., Jha, B., Rao, A.: Distributed deep learning using volunteer computing-like paradigm. In: IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum, pp. 933\u2013942 (2021)","DOI":"10.1109\/IPDPSW52791.2021.00144"},{"key":"1_CR33","unstructured":"Diskin, M., et\u00a0al.: Distributed deep learning in open collaborations. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 7879\u20137897 (2021)"},{"key":"1_CR34","unstructured":"Borzunov, A., et al.: Training transformers together. In: Advances in Neural Information Processing Systems (2022)"},{"key":"1_CR35","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"A Barredo Arrieta","year":"2020","unstructured":"Barredo Arrieta, A., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82\u2013115 (2020)","journal-title":"Inf. Fusion"},{"issue":"5","key":"1_CR36","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin, C.: Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nat. Mach. Intell. 1(5), 206\u2013215 (2019)","journal-title":"Nat. Mach. Intell."},{"key":"1_CR37","unstructured":"McCallum, A.K.: Reinforcement learning with selective perception and hidden state. University of Rochester (1996)"},{"key":"1_CR38","unstructured":"Pyeatt, L.D., Howe, A.E., et al.: Decision tree function approximation in reinforcement learning. In: International Symposium on Adaptive Systems: Evolutionary Computation and Probabilistic Graphical Models, vol. 2, pp. 70\u201377 (2001)"},{"key":"1_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1007\/978-3-642-17537-4_83","volume-title":"Neural Information Processing. Theory and Algorithms","author":"HB Saghezchi","year":"2010","unstructured":"Saghezchi, H.B., Asadpour, M.: Multivariate decision tree function approximation for reinforcement learning. In: Wong, K.W., Mendis, B., Bouzerdoum, A. (eds.) ICONIP 2010. LNCS, vol. 6443, pp. 687\u2013694. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-17537-4_83"},{"key":"1_CR40","unstructured":"Uther, W.T., Veloso, M.M.: Tree based discretization for continuous state space reinforcement learning. In: AAAI Innovative Applications of Artificial Intelligence, vol. 98, pp. 769\u2013774 (1998)"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Hwang, K., Yang, T., Lin, C.: Self organizing decision tree based on reinforcement learning and its application on state space partition. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 6, pp. 5088\u20135093 (2006)","DOI":"10.1109\/ICSMC.2006.385115"},{"key":"1_CR42","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.ins.2012.06.009","volume":"213","author":"KS Hwang","year":"2012","unstructured":"Hwang, K.S., Chen, Y.J., Jiang, W.C., Yang, T.W.: Induced states in a decision tree constructed by Q-learning. Inf. Sci. 213, 39\u201349 (2012)","journal-title":"Inf. Sci."},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Hwang, K., Chen, Y.: Tree-like function approximator in reinforcement learning. In: Annual Conference of the IEEE Industrial Electronics Society, pp. 904\u2013907 (2007)","DOI":"10.1109\/IECON.2007.4460012"},{"key":"1_CR44","unstructured":"Liang, Y., Machado, M.C., Talvitie, E., Bowling, M.: State of the art control of Atari games using shallow reinforcement learning (2016). arXiv:1512.01563"},{"key":"1_CR45","unstructured":"Malagon, M., Ceberio, J.: Evolving neural networks in reinforcement learning by means of UMDAc (2019). arXiv:1904.10932"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Virgolin, M., De\u00a0Lorenzo, A., Medvet, E., Randone, F.: Learning a formula of interpretability to learn interpretable formulas (2020). arXiv:2004.11170","DOI":"10.1007\/978-3-030-58115-2_6"},{"key":"1_CR47","unstructured":"Barcel\u00f3, P., Monet, M., P\u00e9rez, J., Subercaseaux, B.: Model interpretability through the lens of computational complexity (2020). arXiv:2010.12265"},{"key":"1_CR48","unstructured":"Frosst, N., Hinton, G.: Distilling a neural network into a soft decision tree (2017). arXiv:1711.09784"},{"key":"1_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/BFb0055930","volume-title":"Genetic Programming","author":"C Ryan","year":"1998","unstructured":"Ryan, C., Collins, J.J., Neill, M.O.: Grammatical evolution: evolving programs for an arbitrary language. In: Banzhaf, W., Poli, R., Schoenauer, M., Fogarty, T.C. (eds.) EuroGP 1998. LNCS, vol. 1391, pp. 83\u201396. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/BFb0055930"},{"key":"1_CR50","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, King\u2019s College, Cambridge United Kingdom (1989)"},{"issue":"6443","key":"1_CR51","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1126\/science.aau6249","volume":"364","author":"M Jaderberg","year":"2019","unstructured":"Jaderberg, M., et al.: Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364(6443), 859\u2013865 (2019)","journal-title":"Science"},{"issue":"1","key":"1_CR52","first-page":"2171","volume":"13","author":"FA Fortin","year":"2012","unstructured":"Fortin, F.A., De Rainville, F.M., Gardner, M., Parizeau, M., Gagn\u00e9, C.: DEAP: evolutionary algorithms made easy. J. Mach. Learn. Res. 13(1), 2171\u20132175 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR53","unstructured":"Brockman, G., et al.: OpenAI Gym (2016). arXiv:1606.01540"},{"key":"1_CR54","unstructured":"Patel, D., Russell, J., Walsh, F., Rahman, T., Sejnowski, T., Siegelmann, H.: Temporally layered architecture for adaptive, distributed and continuous control (2022). arXiv:2301.00723"},{"issue":"7","key":"1_CR55","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1093\/comjnl\/bxz066","volume":"63","author":"Z Xu","year":"2020","unstructured":"Xu, Z., Cao, L., Chen, X.: Deep reinforcement learning with adaptive update target combination. Comput. J. 63(7), 995\u20131003 (2020)","journal-title":"Comput. J."},{"key":"1_CR56","unstructured":"Peng, X.B., Kumar, A., Zhang, G., Levine, S.: Advantage-weighted regression: simple and scalable off-policy reinforcement learning (2019). arXiv:1910.00177"},{"key":"1_CR57","unstructured":"Kenny, E.M., Tucker, M., Shah, J.: Towards interpretable deep reinforcement learning with human-friendly prototypes. In: International Conference on Learning Representations (2023)"},{"key":"1_CR58","unstructured":"Pourchot, A., Sigaud, O.: CEM-RL: combining evolutionary and gradient-based methods for policy search (2019). arXiv:1810.01222"},{"key":"1_CR59","unstructured":"Chu, X.: Policy optimization with penalized point probability distance: an alternative to proximal policy optimization (2018). arXiv:1807.00442"},{"key":"1_CR60","doi-asserted-by":"publisher","first-page":"128077","DOI":"10.1109\/ACCESS.2022.3226446","volume":"10","author":"J Wu","year":"2022","unstructured":"Wu, J., Wu, Q.J., Chen, S., Pourpanah, F., Huang, D.: A-TD3: an adaptive asynchronous twin delayed deep deterministic for continuous action spaces. IEEE Access 10, 128077\u2013128089 (2022)","journal-title":"IEEE Access"},{"key":"1_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, D., Zhang, T., Jia, S., Xu, B.: Multi-sacle dynamic coding improved spiking actor network for reinforcement learning. In: AAAI Conference on Artificial Intelligence, vol. 36, pp. 59\u201367 (2022)","DOI":"10.1609\/aaai.v36i1.19879"},{"key":"1_CR62","doi-asserted-by":"publisher","unstructured":"Videau, M., Leite, A., Teytaud, O., Schoenauer, M.: Multi-objective genetic programming for explainable reinforcement learning. In: Medvet, E., Pappa, G., Xue, B. (eds.) EuroGP 2022. LNCS, vol. 13223, pp. 278\u2013293. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-02056-8_18","DOI":"10.1007\/978-3-031-02056-8_18"}],"container-title":["Lecture Notes in Computer Science","Applications of Evolutionary Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-90065-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T03:08:42Z","timestamp":1745377722000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-90065-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031900648","9783031900655"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-90065-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"17 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoApplications","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on the Applications of Evolutionary Computation (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Trieste","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evoapplications2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2025\/evoapps\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}