{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:16:37Z","timestamp":1743099397745,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"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_8","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:29:12Z","timestamp":1667518152000},"page":"106-119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PRAG: Periodic Regularized Action Gradient for\u00a0Efficient Continuous Control"],"prefix":"10.1007","author":[{"given":"Xihui","family":"Li","sequence":"first","affiliation":[]},{"given":"Zhongjian","family":"Qiao","sequence":"additional","affiliation":[]},{"given":"Aicheng","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Jiafei","family":"Lyu","sequence":"additional","affiliation":[]},{"given":"Chenghui","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jiangpeng","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Baird, L.: Residual algorithms: reinforcement learning with function approximation. In: Machine Learning Proceedings. Elsevier, pp. 30\u201337 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"8_CR2","unstructured":"Balduzzi, D., Ghifary, M.: Compatible value gradients for reinforcement learning of continuous deep policies. arXiv preprint arXiv:1509.03005 (2015)"},{"key":"8_CR3","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"8_CR4","first-page":"313","volume":"33","author":"P D\u2019Oro","year":"2020","unstructured":"D\u2019Oro, P., Ja\u015bkowski, W.: How to learn a useful critic? Model-based action-gradient-estimator policy optimization. Adv. Neural. Inf. Process. Syst. 33, 313\u2013324 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Drucker, H., LeCun, Y.: Improving generalization performance using double backpropagation. IEEE Trans. Neural Netw. 36, 991\u2013997 (1992)","DOI":"10.1109\/72.165600"},{"key":"8_CR6","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International conference on machine learning. PMLR, pp. 1587\u20131596 (2018)"},{"key":"8_CR7","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. arXiv: Learning (2018)"},{"key":"8_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2015)"},{"key":"8_CR9","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, p. 12 (1999)"},{"key":"8_CR10","unstructured":"Kuznetsov, A., Shvechikov, P., Grishin, A., Vetrov, D.P.: Controlling overestimation bias with truncated mixture of continuous distributional quantile critics. arXiv preprint arXiv:2005.04269 (2020)"},{"issue":"4","key":"8_CR11","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/THMS.2019.2912447","volume":"49","author":"G Li","year":"2019","unstructured":"Li, G., Gomez, R., Nakamura, K., He, B.: Human-centered reinforcement learning: a survey. IEEE Trans. Human-Mach. Syst. 49(4), 337\u2013349 (2019)","journal-title":"IEEE Trans. Human-Mach. Syst."},{"key":"8_CR12","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"8_CR13","unstructured":"Liu, Y., Zeng, Y., Chen, Y., Tang, J., Pan, Y.: Self-improving generative adversarial reinforcement learning. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pp. 52\u201360 (2019)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Lyu, J., Ma, X., Yan, J., Li, X.: Efficient continuous control with double actors and regularized critics. In: Thirty-sixth AAAI Conference on Artificial Intelligence (2022)","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"8_CR15","unstructured":"Lyu, J., Yang, Y., Yan, J., Li, X.: Value activation for bias alleviation: generalized-activated deep double deterministic policy gradients. arXiv preprint arXiv:2112.11216 (2021)"},{"issue":"2","key":"8_CR16","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1287\/mnsc.1060.0614","volume":"53","author":"S Mannor","year":"2007","unstructured":"Mannor, S., Simester, D., Sun, P., Tsitsiklis, J.N.: Bias and variance approximation in value function estimates. Manage. Sci. 53(2), 308\u2013322 (2007)","journal-title":"Manage. Sci."},{"key":"8_CR17","unstructured":"Pan, L., Cai, Q., Huang, L.: Softmax deep double deterministic policy gradients. arXiv preprint arXiv:2010.09177 (2020)"},{"key":"8_CR18","unstructured":"Pendrith, M.D., Ryan, M.R., et al.: Estimator Variance in Reinforcement Learning: Theoretical Problems and Practical Solutions. University of New South Wales, School of Computer Science and Engineering (1997)"},{"issue":"11","key":"8_CR19","doi-asserted-by":"publisher","first-page":"3698","DOI":"10.4249\/scholarpedia.3698","volume":"5","author":"J Peters","year":"2010","unstructured":"Peters, J., Bagnell, J.A.: Policy gradient methods. Scholarpedia 5(11), 3698 (2010)","journal-title":"Scholarpedia"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov decision processes. In: Handbooks in Operations Research and Management Science, vol. 2, pp. 331\u2013434 (1990)","DOI":"10.1016\/S0927-0507(05)80172-0"},{"key":"8_CR21","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley (2014)"},{"key":"8_CR22","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning. PMLR, pp. 387\u2013395 (2014)"},{"key":"8_CR23","unstructured":"Smith, A.E., Coit, D.W., Baeck, T., Fogel, D., Michalewicz, Z.: Penalty functions. In: Handbook of Evolutionary Computation, vol. 97, no. 1, p. C5 (1997)"},{"key":"8_CR24","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"issue":"3","key":"8_CR25","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G., et al.: Temporal difference learning and TD-Gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"key":"8_CR26","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. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"8_CR27","unstructured":"Zeiler, M.: ADADELTA: an adaptive learning rate method. Computer Science (2012)"}],"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_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:38:45Z","timestamp":1667518725000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20868-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031208676","9783031208683"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20868-3_8","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)"}}]}}