{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:32:27Z","timestamp":1743150747716,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031368219"},{"type":"electronic","value":"9783031368226"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-36822-6_22","type":"book-chapter","created":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T03:25:54Z","timestamp":1689305154000},"page":"249-260","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Generalization in\u00a0Reinforcement Learning Through Forked Agents"],"prefix":"10.1007","author":[{"given":"Olivier","family":"Moulin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Francois-Lavet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Elbers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Hoogendoorn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,15]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Moulin, O., Francois-Lavet, V., Elbers, P., Hoogendoorn, M.: Improving adaptability to new environments and removing catastrophic forgetting in Reinforcement Learning by using an eco-system of agents arXiv preprint arXiv:2204.06550 (2021)","DOI":"10.1109\/WI-IAT55865.2022.00032"},{"key":"22_CR2","unstructured":"Zhiwei, J., Xuanlin, L., Zhan, L., Shuang, L., Yiran, W., Hao, S.: Improving Policy Optimization with Generalist-Specialist Learning arXiv preprint arXiv:2206.12984 (2022)"},{"key":"22_CR3","unstructured":"Cobbe, K., Klimov, O., Hesse, C., Kim, T., Schulman, J.: Quantifying generalization in reinforcement learning. In: Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research, vol. 97, pp. 1282\u20131289 (2019). https:\/\/proceedings.mlr.press\/v97\/cobbe19a.html"},{"key":"22_CR4","unstructured":"Cobbe, K., Hesse, C., Hilton, J., Schulman, J.: Lever- aging procedural generation to benchmark reinforcement learning. In International Conference on Machine Learning, pp. 2048\u20132056. PMLR, 2020a (2020)"},{"key":"22_CR5","unstructured":"Ghosh, D., Singh, A., Rajeswaran, A., Kumar, V., Levine, S.: Divide-and-conquer reinforcement learning (2017). arXiv preprint arXiv:1711.09874 (2017)"},{"key":"22_CR6","unstructured":"Justesen, N., Torrado, R.R., Bontrager, P., Khalifa, A., Togelius, J., Risi, S.: Illuminating generalization in deep reinforcement learning through procedural level generation. arXiv preprint arXiv:1806.10729 (2018)"},{"key":"22_CR7","unstructured":"Ghiassian, S., Rafiee, B., Lo, Y.L., White, A.: Improving performance in reinforcement learning by breaking generalization in neural networks. arXiv preprint arXiv:2003.07417 (2020)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (vol. 30, no. 1) (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"22_CR9","unstructured":"Nichol, A., Pfau, V., Hesse, C., Klimov, O., Schulman, J.: Gotta learn fast: A new benchmark for generalization in RL. arXiv preprint arXiv:1804.03720 (2018)"},{"key":"22_CR10","unstructured":"Packer, C., Gao, K., Kos, J., Kr\u00e4henb\u00fchl, P., Koltun, V., Song, D.: Assessing generalization in deep reinforcement learning. arXiv preprint arXiv:1810.12282 (2018)"},{"key":"22_CR11","unstructured":"Raffin, A., et al.: Stable Baselines3 (2019). https:\/\/github.com\/DLR-RM\/stable-baselines3"},{"key":"22_CR12","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic Gridworld Environment for OpenAI Gym (2018). https:\/\/github.com\/maximecb\/gym-minigrid"},{"key":"22_CR13","unstructured":"Konda, V., Tsitsiklis, J.: Actor-Critic algorithms. In: Advances in Neural Information Processing Systems, vol. 12. (NIPS 1999) (1999)"},{"key":"22_CR14","unstructured":"Igl, M., et al.: Generalization in reinforcement learning with selective noise injection and information bottleneck. arXiv preprint arXiv:1910.12911 (2019)"},{"key":"22_CR15","unstructured":"Sonar, A., Pacelli, V., Majumdar, A.: Invariant policy optimization: towards stronger generalization in reinforcement learning. In: Learning for Dynamics and Control, pp. 21\u201333. PMLR (2021)"},{"key":"22_CR16","unstructured":"Chen, J.Z.: Reinforcement Learning Generalization with Surprise Minimization. arXiv preprint arXiv:2004.12399 (2020)"},{"key":"22_CR17","unstructured":"Lu, X., Lee, K., Abbeel, P., Tiomkin, S.: Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning. arXiv preprint arXiv:2008.00614 (2020)"},{"key":"22_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Boulila, W., Driss, M., Alshanqiti, E., Al-Sarem, M., Saeed, F., Krichen, M.: Weight Initialization Techniques for Deep Learning Algorithms in Remote Sensing: Recent Trends and Future Perspectives arXiv:2102.07004 (2021)","DOI":"10.1007\/978-981-16-5559-3_39"},{"issue":"2009","key":"22_CR20","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10(2009), 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR21","unstructured":"Stable baselines 3. Details on stable baselines 3 PPO implementation. https:\/\/spinningup.openai.com\/en\/latest\/algorithms\/ppo.html"},{"key":"22_CR22","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Moulin, O., Francois-Lavet, V., Elbers, P., Hoogendoorn, M.: Improving generalization in reinforcement learning through forked agents, previous version of this paper, arXiv preprint, arXiv:2212.06451 (2022)","DOI":"10.1007\/978-3-031-36822-6_22"}],"container-title":["Lecture Notes in Computer Science","Advances and Trends in Artificial Intelligence. Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-36822-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,17]],"date-time":"2023-12-17T02:12:12Z","timestamp":1702779132000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-36822-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031368219","9783031368226"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-36822-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IEA\/AIE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ieaaie2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ieaaie2023.com\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"129","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":"50","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":"20","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":"39% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}