{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:20:34Z","timestamp":1774671634661,"version":"3.50.1"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030638221","type":"print"},{"value":"9783030638238","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":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63823-8_51","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T16:09:10Z","timestamp":1605715750000},"page":"439-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Stable Training of Bellman Error in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Chen","family":"Gong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpeng","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinwen","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,17]]},"reference":[{"key":"51_CR1","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"51_CR2","unstructured":"Espeholt, L., Soyer, H., Munos, et al.: Impala: scalable distributed deep-rl with importance weighted actor-learner architectures. arXiv preprint arXiv:1802.01561 (2018)"},{"key":"51_CR3","doi-asserted-by":"crossref","unstructured":"Hessel, M., Modayil, J., Hasselt, V., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"51_CR4","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in neural information processing systems, pp. 1008\u20131014 (2000)"},{"key":"51_CR5","first-page":"2378","volume":"29","author":"Q Liu","year":"2016","unstructured":"Liu, Q., Wang, D.: Stein variational gradient descent: a general purpose Bayesian inference algorithm. Adv. Neural Inf. Process. Syst. 29, 2378\u20132386 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"51_CR6","first-page":"8854","volume":"31","author":"Q Liu","year":"2018","unstructured":"Liu, Q., Wang, D.: Stein variational gradient descent as moment matching. Adv. Neural Inf. Process. Syst. 31, 8854\u20138863 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"51_CR7","unstructured":"Liu, Y., et al.: Stein Variational Policy Gradient. arXiv:1704.02399 (2017)"},{"key":"51_CR8","unstructured":"Mnih, V., Badia, A.P., Mirza, M., et al.: Asynchronous methods for deep reinforcement learning. In: International conference on machine learning, pp. 1928\u20131937 (2016)"},{"key":"51_CR9","doi-asserted-by":"publisher","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"key":"51_CR10","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"51_CR11","unstructured":"Nachum, O., Gu, S.S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 3303\u20133313 (2018)"},{"key":"51_CR12","unstructured":"Pearce, T., Anastassacos, N., Zaki, M., Neely, A.: Bayesian inference with anchored ensembles of neural networks, and application to reinforcement learning. arXiv preprint arXiv:1805.11324 (2018)"},{"key":"51_CR13","unstructured":"Pearce, T., Zaki, M., Brintrup, A., Anastassacos, N., Neely, A.: Uncertainty in neural networks: Bayesian ensembling. arXiv preprint arXiv:1810.05546 (2018)"},{"key":"51_CR14","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"51_CR15","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":"51_CR16","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"51_CR17","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms (2014)"},{"key":"51_CR18","doi-asserted-by":"crossref","unstructured":"Tang, J., Qu, M., Wang, M., et al.: Line: Large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web, pp. 1067\u20131077 (2015)","DOI":"10.1145\/2736277.2741093"},{"key":"51_CR19","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581 (2015)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63823-8_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T03:26:48Z","timestamp":1619234808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63823-8_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638221","9783030638238"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63823-8_51","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"17 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)"}}]}}