{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:43:31Z","timestamp":1775123011406,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031301100","type":"print"},{"value":"9783031301117","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-30111-7_49","type":"book-chapter","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T05:02:51Z","timestamp":1681275771000},"page":"579-590","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Evolutionary Action Selection for\u00a0Gradient-Based Policy Learning"],"prefix":"10.1007","author":[{"given":"Yan","family":"Ma","sequence":"first","affiliation":[]},{"given":"Tianxing","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Bingsheng","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"49_CR1","first-page":"487","volume":"10","author":"D Ackley","year":"1992","unstructured":"Ackley, D.: Interactions between learning and evolution. Artif. Life II 10, 487\u2013509 (1992)","journal-title":"Artif. Life II"},{"key":"49_CR2","doi-asserted-by":"crossref","unstructured":"Bodnar, C., Day, B., Li\u00f3, P.: Proximal distilled evolutionary reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3283\u20133290 (2020)","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"49_CR3","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"49_CR4","unstructured":"Casas, N.: Deep deterministic policy gradient for urban traffic light control. arXiv preprint arXiv:1703.09035 (2017)"},{"key":"49_CR5","unstructured":"Colas, C., Sigaud, O., Oudeyer, P.Y.: GEP-PG: decoupling exploration and exploitation in deep reinforcement learning algorithms. In: International Conference on Machine Learning, pp. 1039\u20131048. PMLR (2018)"},{"issue":"7553","key":"49_CR6","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1038\/nature14422","volume":"521","author":"A Cully","year":"2015","unstructured":"Cully, A., Clune, J., Tarapore, D., Mouret, J.B.: Robots that can adapt like animals. Nature 521(7553), 503\u2013507 (2015)","journal-title":"Nature"},{"issue":"1","key":"49_CR7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"PT De Boer","year":"2005","unstructured":"De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134(1), 19\u201367 (2005). https:\/\/doi.org\/10.1007\/s10479-005-5724-z","journal-title":"Ann. Oper. Res."},{"key":"49_CR8","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1587\u20131596. PMLR (2018)"},{"key":"49_CR9","unstructured":"Grefenstette, J.J., Moriarty, D.E., Schultz, A.C.: Evolutionary algorithms for reinforcement learning. arXiv e-prints, p. arXiv-1106 (2011)"},{"key":"49_CR10","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"},{"key":"49_CR11","doi-asserted-by":"crossref","unstructured":"Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of ICNN\u201995-International Conference on Neural Networks, vol. 4, pp. 1942\u20131948. IEEE (1995)","DOI":"10.1109\/ICNN.1995.488968"},{"key":"49_CR12","unstructured":"Khadka, S., et al.: Collaborative evolutionary reinforcement learning. In: International Conference on Machine Learning, pp. 3341\u20133350. PMLR (2019)"},{"key":"49_CR13","unstructured":"Khadka, S., Tumer, K.: Evolution-guided policy gradient in reinforcement learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 1196\u20131208 (2018)"},{"key":"49_CR14","unstructured":"Lee, K., Lee, B.U., Shin, U., Kweon, I.S.: An efficient asynchronous method for integrating evolutionary and gradient-based policy search. arXiv preprint arXiv:2012.05417 (2020)"},{"key":"49_CR15","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"49_CR16","doi-asserted-by":"crossref","unstructured":"Majid, A.Y., Saaybi, S., van Rietbergen, T., Francois-Lavet, V., Prasad, R.V., Verhoeven, C.: Deep reinforcement learning versus evolution strategies: a comparative survey. arXiv preprint arXiv:2110.01411 (2021)","DOI":"10.36227\/techrxiv.14679504"},{"key":"49_CR17","unstructured":"Marchesini, E., Corsi, D., Farinelli, A.: Genetic soft updates for policy evolution in deep reinforcement learning. In: International Conference on Learning Representations (2021)"},{"key":"49_CR18","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3927.001.0001","volume-title":"An Introduction to Genetic Algorithms","author":"M Mitchell","year":"1998","unstructured":"Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press, Cambridge (1998)"},{"key":"49_CR19","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"49_CR20","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6292\u20136299. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"49_CR21","doi-asserted-by":"crossref","unstructured":"Pierrot, T., et al.: Diversity policy gradient for sample efficient quality-diversity optimization. In: ICLR Workshop on Agent Learning in Open-Endedness (2022)","DOI":"10.1145\/3512290.3528845"},{"key":"49_CR22","unstructured":"Pourchot, A., Sigaud, O.: CEM-RL: combining evolutionary and gradient-based methods for policy search. In: International Conference on Learning Representations (2019)"},{"key":"49_CR23","doi-asserted-by":"crossref","unstructured":"Qian, H., Yu, Y.: Derivative-free reinforcement learning: a review. arXiv preprint arXiv:2102.05710 (2021)","DOI":"10.1007\/s11704-020-0241-4"},{"key":"49_CR24","unstructured":"Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint arXiv:1703.03864 (2017)"},{"key":"49_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"49_CR26","unstructured":"Fujimoto, S.: Open-source implementation for TD3. https:\/\/github.com\/sfujim\/TD3 (2018)"},{"key":"49_CR27","doi-asserted-by":"crossref","unstructured":"Sigaud, O.: Combining evolution and deep reinforcement learning for policy search: a survey. arXiv preprint arXiv:2203.14009 (2022)","DOI":"10.1145\/3569096"},{"issue":"7587","key":"49_CR28","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"49_CR29","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. PMLR (2014)"},{"key":"49_CR30","unstructured":"Such, F.P., Madhavan, V., Conti, E., Lehman, J., Stanley, K.O., Clune, J.: Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv preprint arXiv:1712.06567 (2017)"},{"key":"49_CR31","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"},{"issue":"2","key":"49_CR32","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s00500-016-2474-6","volume":"22","author":"D Wang","year":"2018","unstructured":"Wang, D., Tan, D., Liu, L.: Particle swarm optimization algorithm: an overview. Soft. Comput. 22(2), 387\u2013408 (2018)","journal-title":"Soft. Comput."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30111-7_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T03:27:52Z","timestamp":1729222072000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30111-7_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031301100","9783031301117"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30111-7_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"13 April 2023","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":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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","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":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}