{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:31:00Z","timestamp":1742931060827,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819983902"},{"type":"electronic","value":"9789819983919"}],"license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"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\/978-981-99-8391-9_28","type":"book-chapter","created":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T16:02:21Z","timestamp":1701014541000},"page":"350-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Non-stationarity Detection in\u00a0Model-Free Reinforcement Learning via\u00a0Value Function Monitoring"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8325-9529","authenticated-orcid":false,"given":"Maryem","family":"Hussein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5749-0408","authenticated-orcid":false,"given":"Marwa","family":"Keshk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3204-0712","authenticated-orcid":false,"given":"Aya","family":"Hussein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,27]]},"reference":[{"key":"28_CR1","unstructured":"Achiam, J.: Spinning up in deep reinforcement learning. GitHub repository (2018)"},{"key":"28_CR2","unstructured":"Al-Shedivat, M., Bansal, T., Burda, Y., Sutskever, I., Mordatch, I., Abbeel, P.: Continuous adaptation via meta-learning in nonstationary and competitive environments. In: International Conference on Learning Representations (2018)"},{"issue":"6","key":"28_CR3","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: a brief survey. IEEE Sig. Process. Mag. 34(6), 26\u201338 (2017)","journal-title":"IEEE Sig. Process. Mag."},{"key":"28_CR4","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"key":"28_CR5","unstructured":"Canonaco, G., Restelli, M., Roveri, M.: Model-free non-stationarity detection and adaptation in reinforcement learning. In: Proceedings of the Twenty-Fourth European Conference on Artificial Intelligence, ECAI, pp. 1047\u20131054. IOS Press (2020)"},{"key":"28_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1007\/3-540-44565-X_12","volume-title":"Sequence Learning","author":"SPM Choi","year":"2000","unstructured":"Choi, S.P.M., Yeung, D.-Y., Zhang, N.L.: Hidden-mode Markov decision processes for nonstationary sequential decision making. In: Sun, R., Giles, C.L. (eds.) Sequence Learning. LNCS (LNAI), vol. 1828, pp. 264\u2013287. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44565-X_12"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Da Silva, B.C., Basso, E.W., Perotto, F.S., Bazzan, A.L.C., Engel, P.M.: Improving reinforcement learning with context detection. In: Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent systems, pp. 810\u2013812 (2006)","DOI":"10.1145\/1160633.1160779"},{"key":"28_CR8","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR (2017)"},{"key":"28_CR9","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: Proceedings of the Thirty-Fifth International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"28_CR10","unstructured":"Gamrian, S., Goldberg, Y.: Transfer learning for related reinforcement learning tasks via image-to-image translation. In: International Conference on Machine Learning, pp. 2063\u20132072. PMLR (2019)"},{"key":"28_CR11","unstructured":"Hadoux, E., Beynier, A., Weng, P.: Sequential decision-making under non-stationary environments via sequential change-point detection. In: Learning Over Multiple Contexts (LMCE) (2014)"},{"issue":"6443","key":"28_CR12","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"},{"key":"28_CR13","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, vol. 12 (1999)"},{"key":"28_CR14","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. In: NIPS Deep Learning Workshop (2013)"},{"key":"28_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-642-27645-3_1","volume-title":"Reinforcement Learning","author":"M van Otterlo","year":"2012","unstructured":"van Otterlo, M., Wiering, M.: Reinforcement learning and Markov decision processes. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning. ALO, vol. 12, pp. 3\u201342. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_1"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Pope, A.P., et al.: Hierarchical reinforcement learning for air-to-air combat. arXiv preprint arXiv:2105.00990 (2021)","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"key":"28_CR17","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.jmsy.2018.04.004","volume":"48","author":"G Qiao","year":"2018","unstructured":"Qiao, G., Weiss, B.A.: Quick health assessment for industrial robot health degradation and the supporting advanced sensing development. J. Manuf. Syst. 48, 51\u201359 (2018). Special Issue on Smart Manufacturing","journal-title":"J. Manuf. Syst."},{"issue":"268","key":"28_CR18","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR19","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"7","key":"28_CR20","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10(7), 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR21","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 5824\u20135836. Curran Associates, Inc. (2020)"}],"container-title":["Lecture Notes in Computer Science","AI 2023: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8391-9_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:47:16Z","timestamp":1710355636000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8391-9_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"ISBN":["9789819983902","9789819983919"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8391-9_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,27]]},"assertion":[{"value":"27 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brisbane, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2023.org\/","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":"213","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":"23","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":"59","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":"11% - 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":"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)"}}]}}