{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T05:13:34Z","timestamp":1744953214450,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031208676"},{"type":"electronic","value":"9783031208683"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20868-3_11","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:29:12Z","timestamp":1667518152000},"page":"148-160","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Exploration-Exploitation Trade-off in\u00a0Continuous Action Spaces via\u00a0Q-ensemble"],"prefix":"10.1007","author":[{"given":"Wei","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haihong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueyu","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"11_CR1","unstructured":"Amos, B., Stanton, S., Yarats, D., Wilson, A.G.: On the model-based stochastic value gradient for continuous reinforcement learning. In: Learning for Dynamics and Control, pp. 6\u201320 (2021)"},{"key":"11_CR2","unstructured":"Bai, C., et al.: Principled exploration via optimistic bootstrapping and backward induction. In: International Conference on Machine Learning, pp. 577\u2013587 (2021)"},{"key":"11_CR3","unstructured":"Barth-Maron, G., et al.: Distributed distributional deterministic policy gradients. arXiv preprint arXiv:1804.08617 (2018)"},{"key":"11_CR4","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"11_CR5","unstructured":"Chen, R.Y., Sidor, S., Abbeel, P., Schulman, J.: Ucb exploration via q-ensembles. arXiv preprint arXiv:1706.01502 (2017)"},{"key":"11_CR6","unstructured":"Chen, X., Wang, C., Zhou, Z., Ross, K.: Randomized ensembled double q-learning: Learning fast without a model. In: International Conference on Learning Representations (2021)"},{"key":"11_CR7","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1582\u20131591 (2018)"},{"key":"11_CR8","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1856\u20131865 (2018)"},{"key":"11_CR9","unstructured":"Hiraoka, T., Imagawa, T., Hashimoto, T., Onishi, T., Tsuruoka, Y.: Dropout q-functions for doubly efficient reinforcement learning. arXiv preprint arXiv:2110.02034 (2021)"},{"key":"11_CR10","unstructured":"Janner, M., Fu, J., Zhang, M., Levine, S.: When to trust your model: Model-based policy optimization. In: Advances in Neural Information Processing Systems, pp. 12498\u201312509 (2019)"},{"key":"11_CR11","unstructured":"Kaiser, L., et al.: Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374 (2019)"},{"issue":"11","key":"11_CR12","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"11_CR13","first-page":"18560","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Gupta, A., Levine, S.: Discor: corrective feedback in reinforcement learning via distribution correction. Adv. Neural. Inf. Process. Syst. 33, 18560\u201318572 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR14","unstructured":"Mendonca, R., Gupta, A., Kralev, R., Abbeel, P., Levine, S., Finn, C.: Guided meta-policy search. In: Advances in Neural Information Processing Systems, pp. 9653\u20139664 (2019)"},{"key":"11_CR15","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"11_CR16","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":"11_CR17","unstructured":"Osband, I., Van Roy, B., Wen, Z.: Generalization and exploration via randomized value functions. In: International Conference on Machine Learning, pp. 2377\u20132386 (2016)"},{"key":"11_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"11_CR19","unstructured":"Sheikh, H.U., Phielipp, M., B\u00f6l\u00f6ni, L.: Maximizing ensemble diversity in deep q-learning. arXiv preprint arXiv:2006.13823 (2020)"},{"key":"11_CR20","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395 (2014)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033 (2012)","DOI":"10.1109\/IROS.2012.6386109"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2022: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20868-3_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:38:12Z","timestamp":1667518692000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20868-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031208676","9783031208683"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20868-3_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shangai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pricai.org\/2022\/","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":"432","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":"91","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":"39","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":"21% - 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":"7-8","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":"n\/a","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)"}}]}}