{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:35:32Z","timestamp":1743042932318,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031488849"},{"type":"electronic","value":"9783031488856"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-48885-6_3","type":"book-chapter","created":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T11:02:20Z","timestamp":1704193340000},"page":"33-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Sample Efficiency in\u00a0Evolutionary RL Using Off-Policy Ranking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0482-271X","authenticated-orcid":false,"given":"S. R.","family":"Eshwar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8689-2318","authenticated-orcid":false,"given":"Shishir","family":"Kolathaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5066-6589","authenticated-orcid":false,"given":"Gugan","family":"Thoppe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,3]]},"reference":[{"key":"3_CR1","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"3_CR2","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\u20131338. PMLR (2016)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Eshwar, S., Kolathaya, S., Thoppe, G.: Improving sample efficiency in evolutionary RL using off-policy ranking arXiv:2208.10583 (2023)","DOI":"10.1007\/978-3-031-48885-6_3"},{"key":"3_CR4","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, pp. 1861\u20131870. PMLR (2018)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"3_CR6","unstructured":"Kakade, S., Langford, J.: Approximately optimal approximate reinforcement learning. In: In Proc. 19th International Conference on Machine Learning. Citeseer (2002)"},{"key":"3_CR7","unstructured":"Kallus, N., Uehara, M.: Doubly robust off-policy value and gradient estimation for deterministic policies. Advances in Neural Information Processing Systems 33 (2020)"},{"key":"3_CR8","unstructured":"Kallus, N., Zhou, A.: Policy evaluation and optimization with continuous treatments. In: International Conference on Artificial Intelligence and Statistics, pp. 1243\u20131251. PMLR (2018)"},{"key":"3_CR9","unstructured":"Lagoudakis, M.G., Parr, R.: Model-free least-squares policy iteration. Advances in neural information processing systems 14 (2001)"},{"key":"3_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2020.100694","volume":"56","author":"Z Li","year":"2020","unstructured":"Li, Z., Lin, X., Zhang, Q., Liu, H.: Evolution strategies for continuous optimization: A survey of the state-of-the-art. Swarm Evol. Comput. 56, 100694 (2020)","journal-title":"Swarm Evol. Comput."},{"key":"3_CR11","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. In: ICLR (Poster) (2016)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Liu, G., Zhao, L., Yang, F., Bian, J., Qin, T., Yu, N., Liu, T.Y.: Trust region evolution strategies. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 33, pp. 4352\u20134359 (2019)","DOI":"10.1609\/aaai.v33i01.33014352"},{"key":"3_CR13","unstructured":"Mania, H., Guy, A., Recht, B.: Simple random search of static linear policies is competitive for reinforcement learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. pp. 1805\u20131814 (2018)"},{"issue":"2","key":"3_CR14","first-page":"246","volume":"26","author":"J Matyas","year":"1965","unstructured":"Matyas, J.: Random optimization. Autom. Remote. Control. 26(2), 246\u2013253 (1965)","journal-title":"Autom. Remote. Control."},{"key":"3_CR15","unstructured":"Pourchot, A., Sigaud, O.: Cem-rl: Combining evolutionary and gradient-based methods for policy search. arXiv preprint arXiv:1810.01222 (2018)"},{"key":"3_CR16","unstructured":"Rajeswaran, A., Lowrey, K., Todorov, E., Kakade, S.: Towards generalization and simplicity in continuous control. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. pp. 6553\u20136564 (2017)"},{"key":"3_CR17","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":"3_CR18","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International conference on machine learning. pp. 1889\u20131897. PMLR (2015)"},{"key":"3_CR19","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"3_CR20","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":"3_CR21","unstructured":"Zhang, Y., Ross, K.W.: On-policy deep reinforcement learning for the average-reward criterion. In: International Conference on Machine Learning. pp. 12535\u201312545. PMLR (2021)"}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Performance Evaluation Methodologies and Tools"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48885-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T06:54:31Z","timestamp":1730962471000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48885-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031488849","9783031488856"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48885-6_3","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"type":"print","value":"1867-8211"},{"type":"electronic","value":"1867-822X"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"VALUETOOLS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EAI International Conference on Performance Evaluation Methodologies and Tools","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Crete","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"valuetools2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/valuetools.eai-conferences.org\/2023\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30","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":"9","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":"2","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","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":"3.3","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Only subreviewers under the supervision of PC members","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)"}}]}}