{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:25:35Z","timestamp":1743121535068,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030954697"},{"type":"electronic","value":"9783030954703"}],"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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-95470-3_23","type":"book-chapter","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T10:07:13Z","timestamp":1643710033000},"page":"299-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Modular Networks Prevent Catastrophic Interference in Model-Based Multi-task Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Robin","family":"Schiewer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurenz","family":"Wiskott","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,2]]},"reference":[{"key":"23_CR1","unstructured":"Sonnet (2017). https:\/\/github.com\/deepmind\/sonnet"},{"key":"23_CR2","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/"},{"key":"23_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28, 41\u201375 (1997). https:\/\/doi.org\/10.1023\/A:1007379606734","journal-title":"Mach. Learn."},{"key":"23_CR4","unstructured":"Chollet, F., et al.: Keras (2015). https:\/\/keras.io"},{"key":"23_CR5","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems (NIPS), December 2018, pp. 4754\u20134765, May 2018. http:\/\/arxiv.org\/abs\/1805.12114"},{"key":"23_CR6","unstructured":"Duan, Y., Schulman, J., Chen, X., Bartlett, P.L., Sutskever, I., Abbeel, P.: Rl$$^2$$: fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.02779 abs\/1611.02779 (2016). http:\/\/arxiv.org\/abs\/1611.02779"},{"key":"23_CR7","unstructured":"Ebert, F., Finn, C., Dasari, S., Xie, A., Lee, A., Levine, S.: Visual foresight: model-based deep reinforcement learning for vision-based robotic control. arXiv preprint arXiv:1812.00568 (2018)"},{"key":"23_CR8","unstructured":"Feinberg, V., Wan, A., Stoica, I., Jordan, M.I., Gonzalez, J.E., Levine, S.: Model-based value expansion for efficient model-free reinforcement learning. In: Proceedings of the 35th International Conference on Machine Learning (ICML 2018) (2018)"},{"key":"23_CR9","unstructured":"Fernando, C., et al.: PathNet: evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734 (2017)"},{"key":"23_CR10","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR (2017)"},{"key":"23_CR11","unstructured":"Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. arXiv preprint arXiv:1809.01999 abs\/1809.01999 (2018)"},{"key":"23_CR12","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":"23_CR13","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"key":"23_CR14","unstructured":"Hafner, D., Lillicrap, T.P., Norouzi, M., Ba, J.: Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193 abs\/2010.02193 (2020)"},{"key":"23_CR15","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: AAAI, pp. 3215\u20133222 (2018). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/17204"},{"key":"23_CR16","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with Gumbel-Softmax. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings. OpenReview.net (2017)"},{"key":"23_CR17","unstructured":"Kaiser, L., et al.: Model-based reinforcement learning for Atari. arXiv preprint arXiv:1903.00374, March 2019. http:\/\/arxiv.org\/abs\/1903.00374"},{"key":"23_CR18","unstructured":"Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings. OpenReview.net (2017)"},{"key":"23_CR19","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"key":"23_CR20","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"23_CR21","doi-asserted-by":"publisher","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7559\u20137566 (2018). https:\/\/doi.org\/10.1109\/ICRA.2018.8463189","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"23_CR22","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R., Singh, S.: Action-conditional video prediction using deep networks in Atari games. CoRR 10(1), 52\u201355 (2015). http:\/\/papers.nips.cc\/paper\/5859-action-conditional-video-prediction-using-deep-networks-in-atari-games.pdf, http:\/\/arxiv.org\/abs\/1507.08750"},{"key":"23_CR23","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/7a98af17e63a0ac09ce2e96d03992fbc-Paper.pdf"},{"key":"23_CR24","unstructured":"Racani\u00e8re, S., et al.: Imagination-augmented agents for deep reinforcement learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5694\u20135705 (2017)"},{"issue":"1","key":"23_CR25","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/S0377-2217(96)00385-2","volume":"99","author":"RY Rubinstein","year":"1997","unstructured":"Rubinstein, R.Y.: Optimization of computer simulation models with rare events. Eur. J. Oper. Res. 99(1), 89\u2013112 (1997)","journal-title":"Eur. J. Oper. Res."},{"key":"23_CR26","unstructured":"Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 abs\/1606.04671 (2016)"},{"key":"23_CR27","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"23_CR28","unstructured":"Sekar, R., Rybkin, O., Daniilidis, K., Abbeel, P., Hafner, D., Pathak, D.: Planning to explore via self-supervised world models. In: International Conference on Machine Learning, pp. 8583\u20138592. PMLR (2020)"},{"key":"23_CR29","doi-asserted-by":"publisher","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419), 1140\u20131144 (2018). https:\/\/doi.org\/10.1126\/science.aar6404,http:\/\/science.sciencemag.org\/","DOI":"10.1126\/science.aar6404,"},{"issue":"4","key":"23_CR30","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/122344.122377","volume":"2","author":"RS Sutton","year":"1991","unstructured":"Sutton, R.S.: Dyna, an integrated architecture for learning, planning, and reacting. SIGART Bull. 2(4), 160\u2013163 (1991)","journal-title":"SIGART Bull."},{"key":"23_CR31","doi-asserted-by":"publisher","unstructured":"Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38(3), 58\u201368 (1995). https:\/\/doi.org\/10.1145\/203330.203343,https:\/\/dl.acm.org\/doi\/abs\/10.1145\/203330.203343","DOI":"10.1145\/203330.203343,"},{"key":"23_CR32","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/TG.2018.2877047","volume":"11","author":"M Wydmuch","year":"2018","unstructured":"Wydmuch, M., Kempka, M., Ja\u015bkowski, W.: VIZDoom competitions: playing doom from pixels. IEEE Trans. Games 11, 248\u2013259 (2018)","journal-title":"IEEE Trans. Games"},{"key":"23_CR33","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Multi-task reinforcement learning without interference. In: NeurIPS, pp. 1\u20139 (2019)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95470-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T10:16:14Z","timestamp":1643710574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95470-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030954697","9783030954703"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95470-3_23","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":"2 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grasmere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2021.icas.cc\/","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":"215","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":"86","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":"40% - 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":"5-6","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":"1-2","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)"}}]}}