{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:05:09Z","timestamp":1784642709478,"version":"3.55.0"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032191045","type":"print"},{"value":"9783032191052","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-19105-2_2","type":"book-chapter","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:13:46Z","timestamp":1778364826000},"page":"22-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptable Hindsight Experience Replay for\u00a0Search-Based Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2231-5694","authenticated-orcid":false,"given":"Alexandros","family":"Vazaios","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7919-4789","authenticated-orcid":false,"given":"Jannis","family":"Brugger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7475-7546","authenticated-orcid":false,"given":"Cedric","family":"Derstroff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2873-9152","authenticated-orcid":false,"given":"Kristian","family":"Kersting","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6563-7537","authenticated-orcid":false,"given":"Mira","family":"Mezini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"2_CR1","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/453fadbd8a1a3af50a9df4df899537b5-Paper.pdf"},{"key":"2_CR2","unstructured":"Brugger, J., et al.: Neural-guided equation discovery (2025). https:\/\/arxiv.org\/abs\/2503.16953"},{"key":"2_CR3","unstructured":"Derstroff, C., Brugger, J., Bl\u00fcml, J., Mezini, M., Kramer, S., Kersting, K.: Amplifying exploration in monte-carlo tree search by focusing on the unknown (2024). https:\/\/arxiv.org\/abs\/2402.08511"},{"key":"2_CR4","unstructured":"Fang, M., Zhou, T., Du, Y., Han, L., Zhang, Z.: Curriculum-guided hindsight experience replay. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada, pp. 12602\u201312613 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/83715fd4755b33f9c3958e1a9ee221e1-Abstract.html"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Humayoo, M., et al.: Relative importance sampling for off-policy actor-critic in deep reinforcement learning. Sci. Rep. 15 (2025). https:\/\/doi.org\/10.1038\/s41598-025-96201-5","DOI":"10.1038\/s41598-025-96201-5"},{"key":"2_CR6","unstructured":"Lanka, S., Wu, T.: ARCHER: aggressive rewards to counter bias in hindsight experience replay (2018). http:\/\/arxiv.org\/abs\/1809.02070"},{"key":"2_CR7","unstructured":"de\u00a0Lazcano, R., Andreas, K., Tai, J.J., Lee, S.R., Terry, J.: Gymnasium robotics (2024). http:\/\/github.com\/Farama-Foundation\/Gymnasium-Robotics"},{"key":"2_CR8","unstructured":"Moro, L., Likmeta, A., Prati, E., Restelli, M.: Goal-directed planning via hindsight experience replay. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022. OpenReview.net (2022). https:\/\/openreview.net\/forum?id=6NePxZwfae"},{"key":"2_CR9","doi-asserted-by":"publisher","unstructured":"Nguyen, H., La, H.M., Deans, M.C.: Hindsight experience replay with experience ranking. In: Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2019, Oslo, Norway, August 19\u201322, 2019, pp.\u00a01\u20136. IEEE (2019). https:\/\/doi.org\/10.1109\/DEVLRN.2019.8850705, https:\/\/doi.org\/10.1109\/DEVLRN.2019.8850705","DOI":"10.1109\/DEVLRN.2019.8850705"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Poesia, G., Broman, D., Haber, N., Goodman, N.: Learning formal mathematics from intrinsic motivation. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024). https:\/\/openreview.net\/forum?id=uNKlTQ8mBD","DOI":"10.52202\/079017-1362"},{"key":"2_CR11","doi-asserted-by":"publisher","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018). https:\/\/doi.org\/10.1126\/science.aar6404","DOI":"10.1126\/science.aar6404"},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Tan, R.R.P., Ikeda, K., Vergara, J.P.C.: Hindsight-combined and hindsight-prioritized experience replay. In: Yang, H., Pasupa, K., Leung, A.C., Kwok, J.T., Chan, J.H., King, I. (eds.) Neural Information Processing - 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 23\u201327, 2020, Proceedings, Part II. Lecture Notes in Computer Science, vol. 12533, pp. 429\u2013439. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-63833-7_36, https:\/\/doi.org\/10.1007\/978-3-030-63833-7_36","DOI":"10.1007\/978-3-030-63833-7_36"},{"key":"2_CR13","unstructured":"Thakoor, S., Nair, S., Jhunjhunwala, M.: Learning to play othello without human knowledge (2016)"},{"key":"2_CR14","unstructured":"Towers, M., et\u00a0al.: Gymnasium: A standard interface for reinforcement learning environments. arXiv preprint arXiv:2407.17032 (2024)"},{"key":"2_CR15","unstructured":"de\u00a0Vries, J.A., Voskuil, K.S., Moerland, T.M., Plaat, A.: Visualizing muzero models (2021). https:\/\/arxiv.org\/abs\/2102.12924"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-19105-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T13:50:45Z","timestamp":1784641845000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-19105-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032191045","9783032191052"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-19105-2_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}