{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:14:16Z","timestamp":1771697656189,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030638320","type":"print"},{"value":"9783030638337","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-63833-7_38","type":"book-chapter","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T06:03:35Z","timestamp":1605765815000},"page":"452-460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Implicit Posterior Sampling Reinforcement Learning for Continuous Control"],"prefix":"10.1007","author":[{"given":"Shaochen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"38_CR1","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. arXiv preprint arXiv:1707.06887 (2017)"},{"key":"38_CR2","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning (2006)"},{"key":"38_CR3","unstructured":"Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural networks. arXiv, Machine Learning (2015)"},{"key":"38_CR4","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"38_CR5","unstructured":"Cao, Z., Lin, C.T.: Reinforcement learning from hierarchical critics. arXiv preprint arXiv:1902.03079 (2019)"},{"key":"38_CR6","unstructured":"Cao, Z., Wong, K., Lin, C.T.: Human preference scaling with demonstrations for deep reinforcement learning. arXiv preprint arXiv:2007.12904 (2020)"},{"key":"38_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":"38_CR8","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27, pp. 2672\u20132680 (2014)"},{"key":"38_CR9","unstructured":"Ha, D., Dai, A.M., Le, Q.V.: Hypernetworks. In: International Conference on Learning Representations 2017, ICLR 2017 (2017)"},{"key":"38_CR10","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: arXiv preprint arXiv:1801.01290 (2018)"},{"key":"38_CR11","unstructured":"Jiang, B.: Approximate Bayesian computation with Kullback-Leibler divergence as data discrepancy. In: International Conference on Artificial Intelligence and Statistics, pp. 1711\u20131721 (2018)"},{"key":"38_CR12","unstructured":"Krueger, D., Huang, C.W., Islam, R., Turner, R., Lacoste, A., Courville, A.: Bayesian hypernetworks. arXiv, Machine Learning (2018)"},{"key":"38_CR13","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Lipton, Z., Li, X., Gao, J., Li, L., Ahmed, F., Deng, L.: BBQ-networks: efficient exploration in deep reinforcement learning for task-oriented dialogue systems. In: AAAI Conference on Artificial Intelligence, AAAI 2018, pp. 5237\u20135244 (2018)","DOI":"10.1609\/aaai.v32i1.11946"},{"issue":"7540","key":"38_CR15","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":"38_CR16","unstructured":"Moerland, T., Broekens, D., Jonker, C.: Efficient exploration with double uncertain value networks. arXiv preprint arXiv:1711.10789 (2017)"},{"key":"38_CR17","unstructured":"Nachum, O., Norouzi, M., Xu, K., Schuurmans, D.: Trust-PCL: an off-policy trust region method for continuous control. In: International Conference on Learning Representations 2018, ICLR 2018 (2018)"},{"key":"38_CR18","unstructured":"Osband, I., Blundell, C., Pritzel, A., Roy, B.V.: Deep exploration via bootstrapped DQN. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS 2016, pp. 4033\u20134041 (2016)"},{"key":"38_CR19","unstructured":"Pawlowski, N., Rajchl, M., Glocker, B.: Implicit weight uncertainty in neural networks. arXiv preprint arXiv:1711.01297 (2017)"},{"key":"38_CR20","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. In: International Conference on Learning Representations 2018, ICLR 2018 (2018)"},{"issue":"7676","key":"38_CR21","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"38_CR22","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","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63833-7_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:03:30Z","timestamp":1710327810000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63833-7_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638320","9783030638337"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63833-7_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"20 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","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)"}}]}}