{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:52:07Z","timestamp":1743079927488,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031224188"},{"type":"electronic","value":"9783031224195"}],"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\/978-3-031-22419-5_17","type":"book-chapter","created":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T08:12:54Z","timestamp":1672733574000},"page":"196-207","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Model Compression for\u00a0Deep Reinforcement Learning Through Mutual Information"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1583-7554","authenticated-orcid":false,"given":"Jes\u00fas","family":"Garc\u00eda-Ram\u00edrez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7618-8762","authenticated-orcid":false,"given":"Eduardo F.","family":"Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-3513","authenticated-orcid":false,"given":"Hugo Jair","family":"Escalante","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,4]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"17_CR2","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Neural Information Processing Systems, pp. 1877\u20131901 (2020)"},{"key":"17_CR3","unstructured":"Castro, P.S., Moitra, S., Gelada, C., Kumar, S., Bellemare, M.G.: Dopamine: A research framework for deep reinforcement learning. arXiv preprint arXiv:1812.06110 (2018)"},{"key":"17_CR4","unstructured":"Cheng, Y., Wang, D., Zhou, P., Zhang, T.: A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017)"},{"key":"17_CR5","unstructured":"Cover, T.M.: Elements of Information Theory. John Wiley & Sons (2006)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Universal trading for order execution with oracle policy distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 107\u2013115 (2021)","DOI":"10.1609\/aaai.v35i1.16083"},{"key":"17_CR7","unstructured":"Green, S., Vineyard, C.M., Ko\u00e7, C.K.: Distillation strategies for proximal policy optimization. arXiv preprint arXiv:1901.08128 (2019)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: Deep Learning and Representation Learning Workshop, pp. 1\u20139 (2014)"},{"key":"17_CR10","unstructured":"Liu, X., Liu, S., Li, W., Yang, S., Gao, Y.: Keeping minimal experience to achieve efficient interpretable policy distillation. arXiv preprint arXiv:2203.00822 (2022)"},{"key":"17_CR11","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"17_CR12","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(7540), 529 (2015)","journal-title":"Nature"},{"key":"17_CR13","unstructured":"Parisotto, E., Ba, J.L., Salakhutdinov, R.: Actor-mimic: Deep multitask and transfer reinforcement learning. In: International Conference on Learning Representations, pp. 1\u201316 (2016)"},{"key":"17_CR14","unstructured":"Polino, A., Pascanu, R., Alistarh, D.: Model compression via distillation and quantization. In: International Conference on Learning Representations, pp. 1\u201321 (2018)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"17_CR16","unstructured":"Rusu, A.A., et al.: Policy distillation. In: International Conference on Learning Representation,. pp. 1\u201313 (2015)"},{"key":"17_CR17","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 pp. 1\u201312 (2017)"},{"issue":"3","key":"17_CR18","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379\u2013423 (1948)","journal-title":"Bell Syst. Tech. J."},{"key":"17_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2014)"},{"key":"17_CR20","unstructured":"Sun, Y., Fazli, P.: Real-time policy distillation in deep reinforcement learning, pp. 1\u20136 (2019)"},{"key":"17_CR21","unstructured":"Sun, Y., Fazli, P.: Ensemble policy distillation in deep reinforcement learning. In: Workshop on Reinforcement Learning in Games, pp. 1\u20139 (2020)"},{"key":"17_CR22","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, London (2018)"},{"key":"17_CR23","unstructured":"Xing, J., Nagata, T., Zou, X., Neftci, E., Krichmar, J.L.: Policy distillation with selective input gradient regularization for efficient interpretability. arXiv preprint arXiv:2205.08685 (2022)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Xu, R., Luan, S., Gu, Z., Zhao, Q., Chen, G.: LRP-based policy pruning and distillation of reinforcement learning agents for embedded systems. In: 2022 IEEE 25th International Symposium On Real-Time Distributed Computing (ISORC), pp. 1\u20138. IEEE (2022)","DOI":"10.1109\/ISORC52572.2022.9812837"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence \u2013 IBERAMIA 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22419-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T08:15:33Z","timestamp":1672733733000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22419-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031224188","9783031224195"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22419-5_17","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 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IBERAMIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ibero-American Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cartagena de Indias","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Colombia","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":"23 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 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":"iberamia2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iberamia.org\/iberamia\/iberamia2022\/","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":"EquinOCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","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":"33","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":"4","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":"49% - 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","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)"}}]}}