{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:28:59Z","timestamp":1743013739806,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031138690"},{"type":"electronic","value":"9783031138706"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-13870-6_4","type":"book-chapter","created":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T09:03:13Z","timestamp":1660467793000},"page":"41-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Efficient Evaluation Mechanism for Evolutionary Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Xiaoqiang","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingling","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuzhen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Ming","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,8,15]]},"reference":[{"key":"4_CR1","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, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"4_CR2","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, 354\u2013359 (2017)","journal-title":"Nature"},{"key":"4_CR3","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"key":"4_CR4","unstructured":"Khadka, S., Tumer, K.: Evolution-guided policy gradient in reinforcement learning. In: Advances in Neural Information Processing Systems. pp. 1188\u20131200 (2018)"},{"key":"4_CR5","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":"4_CR6","unstructured":"Rechenberg, I., Eigen, M.: Evolutionsstrategie: Optimierung Technischer Systeme nach Prinzipien der Biologischen Evolution. Frommann-Holzboog Stuttgart (1973)"},{"key":"4_CR7","unstructured":"Salimans, T., Ho, J., Chen, X., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. ArXiv e-prints (2017)"},{"key":"4_CR8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1002\/rob.21958","volume":"38","author":"K Burnett","year":"2021","unstructured":"Burnett, K., Qian, J., Du, X., Liu, L., Yoon, D.J., et al.: Zeus: A system description of the twotime winner of the collegiate SAE autodrive competition. J. Field Robotics 38, 139\u2013166 (2021)","journal-title":"J. Field Robotics"},{"key":"4_CR9","doi-asserted-by":"publisher","first-page":"2454","DOI":"10.1161\/CIRCULATIONAHA.116.026318","volume":"135","author":"JJ Boutilier","year":"2017","unstructured":"Boutilier, J.J., Brooks, S.C., Janmohamed, A., Byers, A., Buick, J.E., et al.: Optimizing a drone network to deliver automated external defibrillators. Circulation 135, 2454\u20132465 (2017)","journal-title":"Circulation"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: A physics engine for model-based control. In: Intelligent Robots and Systems (IROS), 2012 IEEE\/RSJ International Conference on, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Bodnar, C., Day, B., Li\u00f3, P.: Proximal distilled evolutionary reinforcement learning. In Proceedings of the Conference on Artificial Intelligence (AAAI\u201920), pp. 3283\u20133290. AAAI Press (2020)","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"4_CR12","unstructured":"Pourchot, A., Sigaud, O.: CEM-RL: Combining evolutionary and gradient-based methods for policy search. In: International Conference on Learning Representations (2019)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"De Boer, P.-T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Annals of Operations Res. 134(1), 19\u201367 (2005)","DOI":"10.1007\/s10479-005-5724-z"},{"key":"4_CR14","unstructured":"Khadka, S., et al.: Collaborative evolutionary reinforcement learning. In: International Conference on Machine Learning (2019)"},{"key":"4_CR15","unstructured":"Majumdar, S., Khadka, S., Miret, S., Mcaleer, S., Tumer, K.: Evolutionary reinforcement learning for sample-efficient multiagent coordination. In: International Conference on Machine Learning, pp. 6651\u20136660 (2020)"},{"key":"4_CR16","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative competitive environments. In: Advances in Neural Information Processing Systems, pp. 6379\u20136390 (2017)"},{"key":"4_CR17","unstructured":"Zheng, H., Jiang, J., Wei, P., Long, G., Zhang, C.: Competitive and cooperative heterogeneous deep reinforcement learning. In: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS\u201920, pp. 1656\u20131664, Richland, SC (2020)"},{"key":"4_CR18","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning (2018)"},{"key":"4_CR19","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 (2018)"},{"key":"4_CR20","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"4_CR21","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"4_CR22","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: International Conference on Machine Learning, pp. 1329\u2013 1338 (2016)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. arXiv preprint arXiv:1709.06560 (2017)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"4_CR24","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":"4_CR25","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Ye, D., et al.: Mastering complex control in MOBA games with deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 6672\u20136679 (2020)","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"4_CR27","unstructured":"Dhariwal, P., et al.: Openai Baselines. https:\/\/github.com\/openai\/baselines (2017)"},{"key":"4_CR28","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u2013 1937 (2016)"},{"key":"4_CR29","unstructured":"Cobbe, K.W., Hilton, J., Klimov, O., Schulman, J.: Phasic policy gradient, In: International Conference on Machine Learning, PMLR, pp. 2020\u20132027 (2021)"},{"key":"4_CR30","unstructured":"Hasselt, V.H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2094\u20132100 (2016)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: Combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"4_CR32","unstructured":"Conti, E., Madhavan, V., Such, F.P., Lehman, J., Stanley, K.O., Clune, J.: Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents. arXiv preprint arXiv:1712.06560 (2017)"},{"issue":"7553","key":"4_CR33","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 (2015)","journal-title":"Nature"},{"key":"4_CR34","unstructured":"Lehman, J., Stanley, K.O.: Exploiting open-endedness to solve problems through the search for novelty. In: ALIFE, pp. 329\u2013336 (2008)"},{"key":"4_CR35","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3389\/frobt.2016.00040","volume":"3","author":"JK Pugh","year":"2016","unstructured":"Pugh, J.K., Soros, L.B., Stanley, K.O.: Quality diversity: a new frontier for evolutionary computation. Frontiers in Robotics and AI 3, 40 (2016)","journal-title":"Frontiers in Robotics and AI"}],"container-title":["Lecture Notes in Computer Science","Intelligent Computing Theories and Application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-13870-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:54:11Z","timestamp":1709830451000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13870-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031138690","9783031138706"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13870-6_4","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":"15 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","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":"7 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2022\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"IC-ICC-CN","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"449","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":"209","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":"47% - 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","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":"2.5","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)"}}]}}