{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:20:28Z","timestamp":1742912428458,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030862299"},{"type":"electronic","value":"9783030862305"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86230-5_26","type":"book-chapter","created":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T09:03:00Z","timestamp":1631005380000},"page":"325-337","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting \u201cRecurrent World Models Facilitate Policy Evolution\u201d"],"prefix":"10.1007","author":[{"given":"Bernardo","family":"Esteves","sequence":"first","affiliation":[]},{"given":"Francisco S.","family":"Melo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,3]]},"reference":[{"key":"26_CR1","unstructured":"Bishop, C.: Mixture density networks. Technical Report NCRG\/94\/004, Neural Computing Research Group, Aston University, February 1994"},{"key":"26_CR2","unstructured":"Brockman, G., et al.: OpenAI Gym. CoRR abs\/1606.01540 (2016)"},{"key":"26_CR3","first-page":"5365","volume":"32","author":"A Gaier","year":"2019","unstructured":"Gaier, A., Ha, D.: Weight agnostic neural networks. Adv. Neural Inf. Process. Syst. 32, 5365\u20135378 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"26_CR4","unstructured":"Graves, A.: Generating sequences with recurrent neural networks. CoRR abs\/1308.0850 (2013)"},{"key":"26_CR5","first-page":"2450","volume":"31","author":"D Ha","year":"2018","unstructured":"Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. Adv. Neural Inf. Process. Syst. 31, 2450\u20132462 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"26_CR6","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1162\/106365601750190398","volume":"9","author":"N Hansen","year":"2001","unstructured":"Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evol. Comput. 9(2), 159\u2013195 (2001)","journal-title":"Evol. Comput."},{"issue":"8","key":"26_CR7","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"26_CR8","unstructured":"Kingma, D., Welling, M.: Auto-encoding variational Bayes. In: Proceedings 2nd International Conference on Learning Representations (2014)"},{"key":"26_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014)"},{"key":"26_CR10","unstructured":"Lillicrap, T., et al.: Continuous control with deep reinforcement learning. In: Proceedings of the 4th International Conference Learning Representations (2016)"},{"key":"26_CR11","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":"26_CR12","doi-asserted-by":"crossref","unstructured":"Risi, S., Stanley, K.: Deep neuroevolution of recurrent and discrete world models. In: Proceedings of the 2019 Genetic and Evolutionary Computation Conference, pp. 456\u2013462 (2019)","DOI":"10.1145\/3321707.3321817"},{"key":"26_CR13","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, Shogi, and go through self-play. Science 362, 1140\u20131144 (2018)","journal-title":"Science"},{"key":"26_CR14","unstructured":"Stulp, F., Sigaud, O.: Path integral policy improvement with covariance matrix adaptation. In: Proceedings of the 29th International Conference Machine Learning, pp. 1547\u20131554 (2012)"},{"key":"26_CR15","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"26_CR16","unstructured":"Tallec, C., Blier, L., Kalainathan, D.: Reproducing \u201cWorld Models\u201d: Is training the recurrent network really needed? (2018). https:\/\/ctallec.github.io\/world-models\/"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Tang, Y., Nguyen, D., Ha, D.: Neuroevolution of self-interpretable agents. CoRR abs\/2003.08165 (2020)","DOI":"10.1145\/3377930.3389847"},{"key":"26_CR18","unstructured":"Wang, T., et al.: Benchmarking model-based reinforcement learning. CoRR abs\/1907.02057 (2019)"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86230-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T09:10:13Z","timestamp":1631005813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86230-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030862299","9783030862305"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86230-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"3 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.appia.pt\/epia2021\/","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":"108","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":"62","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":"57% - 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":"3.47","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":"1.36","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)"}}]}}