{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:01:49Z","timestamp":1776888109572,"version":"3.51.2"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031568541","type":"print"},{"value":"9783031568558","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-56855-8_1","type":"book-chapter","created":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T18:01:52Z","timestamp":1711216912000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hindsight Experience Replay with\u00a0Evolutionary Decision Trees for\u00a0Curriculum Goal Generation"],"prefix":"10.1007","author":[{"given":"Erdi","family":"Sayar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladislav","family":"Vintaykin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Iacca","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,21]]},"reference":[{"key":"1_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"},{"key":"1_CR2","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv:1312.5602 (2013)"},{"key":"1_CR3","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"1_CR4","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016)","journal-title":"Nature"},{"key":"1_CR5","unstructured":"Rajeswaran, A., Lowrey, K., Todorov, E.V., Kakade, S.M.: Towards generalization and simplicity in continuous control. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"1_CR6","series-title":"Springer Tracts in Advanced Robotics","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/11552246_35","volume-title":"Experimental Robotics IX","author":"AY Ng","year":"2006","unstructured":"Ng, A.Y., Coates, A., Diel, M., Ganapathi, V., Schulte, J., Tse, B., Berger, E., Liang, E.: Autonomous inverted helicopter flight via reinforcement learning. In: Ang, M.H., Khatib, O. (eds.) Experimental Robotics IX. STAR, vol. 21, pp. 363\u2013372. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11552246_35"},{"key":"1_CR7","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv:1509.02971 (2019)"},{"key":"1_CR8","unstructured":"Zakka, K., et al.: RoboPianist: a benchmark for high-dimensional robot control. arXiv:2304.04150 (2023)"},{"key":"1_CR9","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: International Conference on Machine Learning. (1999)"},{"key":"1_CR10","unstructured":"Rengarajan, D., Vaidya, G., Sarvesh, A., Kalathil, D., Shakkottai, S.: Reinforcement learning with sparse rewards using guidance from offline demonstration. In: International Conference on Learning Representations (2022)"},{"key":"1_CR11","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"1_CR12","unstructured":"Zhao, R., Tresp, V.: Energy-based hindsight experience prioritization. In: Conference on Robot Learning, pp. 113\u2013122. PMLR (2018)"},{"key":"1_CR13","unstructured":"Zhao, R., Sun, X., Tresp, V.: Maximum entropy-regularized multi-goal reinforcement learning. In: International Conference on Machine Learning, pp. 7553\u20137562. PMLR (2019)"},{"key":"1_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/978-3-030-57321-8_5","volume-title":"Machine Learning and Knowledge Extraction","author":"E Puiutta","year":"2020","unstructured":"Puiutta, E., Veith, E.M.S.P.: Explainable reinforcement learning: a survey. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-MAKE 2020. LNCS, vol. 12279, pp. 77\u201395. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-57321-8_5"},{"issue":"3","key":"1_CR15","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3236386.3241340","volume":"16","author":"ZC Lipton","year":"2018","unstructured":"Lipton, Z.C.: The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery. Queue 16(3), 31\u201357 (2018)","journal-title":"Queue"},{"key":"1_CR16","unstructured":"Molnar, C.: Interpretable machine learning. Lulu. com (2020)"},{"key":"1_CR17","unstructured":"Coppens, Y., et al.: Distilling deep reinforcement learning policies in soft decision trees. In: IJCAI Workshop on Explainable Artificial Intelligence, pp. 1\u20136 (2019)"},{"key":"1_CR18","unstructured":"Bastani, O., Pu, Y., Solar-Lezama, A.: Verifiable reinforcement learning via policy extraction. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"1_CR19","unstructured":"Ding, Z., Hernandez-Leal, P., Ding, G.W., Li, C., Huang, R.: CDT: cascading decision trees for explainable reinforcement learning. arXiv:2011.07553 (2020)"},{"key":"1_CR20","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":"1_CR21","doi-asserted-by":"crossref","unstructured":"Hallawa, A., et al.: Evo-RL: evolutionary-driven reinforcement learning. In: Genetic and Evolutionary Computation Conference Companion, pp. 153\u2013154 (2021)","DOI":"10.1145\/3449726.3459475"},{"key":"1_CR22","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_CR23","doi-asserted-by":"crossref","unstructured":"Ferigo, A., Custode, L.L., Iacca, G.: Quality diversity evolutionary learning of decision trees. In: Symposium on Applied Computing, pp. 425\u2013432. ACM\/SIGAPP (2023)","DOI":"10.1145\/3555776.3577591"},{"key":"1_CR24","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_CR25","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, pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/SSCI50451.2021.9660048"},{"key":"1_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110758","volume":"147","author":"M Crespi","year":"2023","unstructured":"Crespi, M., Ferigo, A., Custode, L.L., Iacca, G.: A population-based approach for multi-agent interpretable reinforcement learning. Appl. Soft Comput. 147, 110758 (2023)","journal-title":"Appl. Soft Comput."},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: A physics engine for model-based control. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"1_CR28","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"1_CR29","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv:1509.02971 (2015)"},{"key":"1_CR30","unstructured":"Plappert, M., et al.: Multi-goal reinforcement learning: challenging robotics environments and request for research. arXiv:1802.09464 (2018)"},{"key":"1_CR31","unstructured":"Schaul, T., Horgan, D., Gregor, K., Silver, D.: Universal value function approximators. In: International Conference on Machine Learning. (2015)"},{"key":"1_CR32","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_CR33","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv:1606.01540 (2016)"}],"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\/978-3-031-56855-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T00:18:33Z","timestamp":1711325913000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56855-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031568541","9783031568558"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56855-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"21 March 2024","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":"Aberystwyth","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 March 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 March 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evoapplications2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2024\/evoapps\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","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":"51","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":"0","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":"66% - 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":"3.4","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":"1.7","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)"}}]}}