{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:17:27Z","timestamp":1768072647463,"version":"3.49.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030864859","type":"print"},{"value":"9783030864866","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86486-6_6","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"87-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Periodic Intra-ensemble Knowledge Distillation for Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Zhang-Wei","family":"Hong","sequence":"first","affiliation":[]},{"given":"Prabhat","family":"Nagarajan","sequence":"additional","affiliation":[]},{"given":"Guilherme","family":"Maeda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"6_CR1","unstructured":"Abel, D., Agarwal, A., Diaz, F., Krishnamurthy, A., Schapire, R.E.: Exploratory gradient boosting for reinforcement learning in complex domains. In: International Conference on Machine Learning Workshop on Abstraction in Reinforcement Learning (2016)"},{"key":"6_CR2","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"6_CR3","unstructured":"Conti, E., Madhavan, V., Such, F.P., Lehman, J., Stanley, K., Clune, J.: Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents. In: Advances in Neural Information Processing Systems, pp. 5027\u20135038 (2018)"},{"key":"6_CR4","unstructured":"Czarnecki, W., et al.: Mix & match agent curricula for reinforcement learning. In: International Conference on Machine Learning, pp. 1087\u20131095. PMLR (2018)"},{"key":"6_CR5","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning, pp. 2052\u20132062. PMLR (2019)"},{"issue":"77","key":"6_CR6","first-page":"1","volume":"22","author":"Y Fujita","year":"2021","unstructured":"Fujita, Y., Nagarajan, P., Kataoka, T., Ishikawa, T.: ChainerRL: a deep reinforcement learning library. J. Mach. Learn. Res. 22(77), 1\u201314 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR7","unstructured":"Galashov, A., et al.: Information asymmetry in KL-regularized RL. In: International Conference on Learning Representations (2019)"},{"key":"6_CR8","unstructured":"Gangwani, T., Peng, J.: Policy optimization by genetic distillation. In: International Conference on Learning Representations (2018)"},{"key":"6_CR9","unstructured":"Ghosh, D., Singh, A., Rajeswaran, A., Kumar, V., Levine, S.: Divide-and-conquer reinforcement learning. In: International Conference on Learning Representations (2018)"},{"key":"6_CR10","unstructured":"Gimelfarb, M., Sanner, S., Lee, C.G.: Reinforcement learning with multiple experts: a Bayesian model combination approach. In: Advances in Neural Information Processing Systems, pp. 9528\u20139538 (2018)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Haarnoja, T., Ha, S., Zhou, A., Tan, J., Tucker, G., Levine, S.: Learning to walk via deep reinforcement learning. In: Robotics: Science and Systems XV (2019)","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"6_CR12","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep Q-learning from demonstrations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"6_CR14","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"6_CR15","unstructured":"Hong, Z.W., Shann, T.Y., Su, S.Y., Chang, Y.H., Fu, T.J., Lee, C.Y.: Diversity-driven Exploration Strategy for Deep Reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 10489\u201310500 (2018)"},{"key":"6_CR16","unstructured":"Jung, W., Park, G., Sung, Y.: Population-guided parallel policy search for reinforcement learning. In: International Conference on Learning Representations (2020)"},{"key":"6_CR17","unstructured":"Khadka, S., Tumer, K.: Evolution-guided policy gradient in reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 1188\u20131200 (2018)"},{"key":"6_CR18","unstructured":"Lan, X., Zhu, X., Gong, S.: Knowledge distillation by on-the-fly native ensemble. In: Advances in Neural Information Processing Systems (2018)"},{"key":"6_CR19","unstructured":"Levine, S., Koltun, V.: Guided policy search. In: International Conference on Machine Learning, pp. 1\u20139 (2013)"},{"issue":"7540","key":"6_CR20","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(7540), 529 (2015)","journal-title":"Nature"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: 2018 IEEE International Conference on Robotics and Automation, pp. 7559\u20137566. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE International Conference on Robotics and Automation, pp. 6292\u20136299. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"6_CR23","unstructured":"Oh, J., Guo, Y., Singh, S., Lee, H.: Self-imitation learning. In: International Conference on Machine Learning, pp. 3878\u20133887. PMLR (2018)"},{"key":"6_CR24","unstructured":"Osband, I., Blundell, C., Pritzel, A., Van Roy, B.: Deep exploration via bootstrapped DQN. In: Advances in Neural Information Processing Systems, pp. 4026\u20134034 (2016)"},{"issue":"124","key":"6_CR25","first-page":"1","volume":"20","author":"I Osband","year":"2019","unstructured":"Osband, I., Roy, B.V., Russo, D.J., Wen, Z.: Deep exploration via randomized value functions. J. Mach. Learn. Res. 20(124), 1\u201362 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR26","unstructured":"Rusu, A.A., et al.: Policy distillation. In: International Conference on Learning Representations (2016)"},{"key":"6_CR27","unstructured":"Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint arXiv:1703.03864 (2017)"},{"key":"6_CR28","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897 (2015)"},{"key":"6_CR29","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"6_CR30","unstructured":"Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)"},{"key":"6_CR31","unstructured":"Teh, Y., et al.: Distral: robust multitask reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 4496\u20134506 (2017)"},{"issue":"4","key":"6_CR32","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0921-8890(95)00005-Z","volume":"15","author":"CK Tham","year":"1995","unstructured":"Tham, C.K.: Reinforcement learning of multiple tasks using a hierarchical CMAC architecture. Robot. Auton. Syst. 15(4), 247\u2013274 (1995)","journal-title":"Robot. Auton. Syst."},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, T., Kahn, G., Levine, S., Abbeel, P.: Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search. In: 2016 IEEE International Conference on Robotics and Automation, pp. 528\u2013535. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4320\u20134328 (2018)","DOI":"10.1109\/CVPR.2018.00454"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86486-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:04:40Z","timestamp":1757369080000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86486-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030864859","9783030864866"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86486-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Bilbao","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.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":"869","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":"210","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":"24% - 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":"3-9","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}