{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:30:52Z","timestamp":1757622652917,"version":"3.44.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030864859"},{"type":"electronic","value":"9783030864866"}],"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_8","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"122-138","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3457-2563","authenticated-orcid":false,"given":"Muhammad Rizki","family":"Maulana","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0988-2500","authenticated-orcid":false,"given":"Wee Sun","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"8_CR1","unstructured":"Anschel, O., Baram, N., Shimkin, N.: Averaged-DQN: variance reduction and stabilization for deep reinforcement learning. In: International Conference on Machine Learning, pp. 176\u2013185. PMLR (2017)"},{"key":"8_CR2","unstructured":"Badia, A.P., et al.: Never give up: learning directed exploration strategies. In: International Conference on Learning Representations (2019)"},{"key":"8_CR3","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: International Conference on Machine Learning, pp. 449\u2013458 (2017)"},{"key":"8_CR4","unstructured":"Chen, R.Y., Sidor, S., Abbeel, P., Schulman, J.: UCB exploration via Q-ensembles. arXiv preprint arXiv:1706.01502 (2017)"},{"key":"8_CR5","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems, pp. 4754\u20134765 (2018)"},{"key":"8_CR6","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. In: International Conference on Learning Representations (2018)"},{"key":"8_CR7","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596 (2018)"},{"issue":"1","key":"8_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","volume":"4","author":"S Geman","year":"1992","unstructured":"Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias\/variance dilemma. Neural Comput. 4(1), 1\u201358 (1992)","journal-title":"Neural Comput."},{"key":"8_CR9","unstructured":"van Hasselt, H.P., Hessel, M., Aslanides, J.: When to use parametric models in reinforcement learning? In: Advances in Neural Information Processing Systems, pp. 14322\u201314333 (2019)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-1-4612-4380-9_35","volume-title":"Breakthroughs in Statistics","author":"PJ Huber","year":"1992","unstructured":"Huber, P.J.: Robust estimation of a location parameter. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics, pp. 492\u2013518. Springer, Heidelberg (1992). https:\/\/doi.org\/10.1007\/978-1-4612-4380-9_35"},{"key":"8_CR12","unstructured":"Imani, E., White, M.: Improving regression performance with distributional losses. In: International Conference on Machine Learning, pp. 2157\u20132166 (2018)"},{"key":"8_CR13","unstructured":"Jaderberg, M., et al.: Reinforcement learning with unsupervised auxiliary tasks. arXiv preprint arXiv:1611.05397 (2016)"},{"key":"8_CR14","unstructured":"Kaiser, \u0141., et al.: Model based reinforcement learning for Atari. In: International Conference on Learning Representations (2019)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Kartal, B., Hernandez-Leal, P., Taylor, M.E.: Terminal prediction as an auxiliary task for deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol. 15, pp. 38\u201344 (2019)","DOI":"10.1609\/aiide.v15i1.5222"},{"key":"8_CR16","unstructured":"Kielak, K.: Do recent advancements in model-based deep reinforcement learning really improve data efficiency? arXiv preprint arXiv:2003.10181 (2020)"},{"key":"8_CR17","unstructured":"Kurutach, T., Clavera, I., Duan, Y., Tamar, A., Abbeel, P.: Model-ensemble trust-region policy optimization. In: International Conference on Learning Representations (2018)"},{"key":"8_CR18","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: Curl: contrastive unsupervised representations for reinforcement learning. In: International Conference on Machine Learning, pp. 5639\u20135650. PMLR (2020)"},{"key":"8_CR19","unstructured":"Lee, K., Laskin, M., Srinivas, A., Abbeel, P.: Sunrise: a simple unified framework for ensemble learning in deep reinforcement learning. arXiv preprint arXiv:2007.04938 (2020)"},{"key":"8_CR20","unstructured":"Mirowski, P., et al.: Learning to navigate in complex environments. arXiv preprint arXiv:1611.03673 (2016)"},{"issue":"7540","key":"8_CR21","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\u2013533 (2015)","journal-title":"Nature"},{"key":"8_CR22","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)"},{"key":"8_CR23","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"8_CR24","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction (2011)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Ueda, N., Nakano, R.: Generalization error of ensemble estimators. In: Proceedings of International Conference on Neural Networks (ICNN\u201996), vol. 1, pp. 90\u201395. IEEE (1996)","DOI":"10.1109\/ICNN.1996.548872"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"8_CR27","unstructured":"Wang, Q., Zhang, L., Chi, M., Guo, J.: MTForest: ensemble decision trees based on multi-task learning (2008)"},{"key":"8_CR28","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1995\u20132003. PMLR (2016)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Ye, Q., Munro, P.W.: Improving a neural network classifier ensemble with multi-task learning. In: The 2006 IEEE International Joint Conference on Neural Network Proceedings, pp. 5164\u20135170. IEEE (2006)","DOI":"10.1109\/IJCNN.2006.247247"}],"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_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:05:43Z","timestamp":1757369143000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86486-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030864859","9783030864866"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86486-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}