{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:03:46Z","timestamp":1743077026730,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031301049"},{"type":"electronic","value":"9783031301056"}],"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\/978-3-031-30105-6_34","type":"book-chapter","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T20:31:55Z","timestamp":1681331515000},"page":"406-417","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Context-Adapted Multi-policy Ensemble Method for\u00a0Generalization in\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Tingting","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengge","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsuo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"34_CR1","unstructured":"Justesen, N., Torrado, R., Bontrager, P., Khalifa, A., Togelius, J., Risi, S.: Illuminating generalization in deep reinforcement learning through procedural level generation. arXiv: Learning (2018)"},{"key":"34_CR2","unstructured":"Zhang, C., Vinyals, O., Munos, R., Bengio, S.: A study on overfitting in deep reinforcement learning. arXiv, abs\/1804.06893 (2018)"},{"key":"34_CR3","unstructured":"Gamrian, S., Goldberg, Y.: Transfer learning for related reinforcement learning tasks via image-to-image translation. In: International Conference on Machine Learning. PMLR (2019)"},{"key":"34_CR4","unstructured":"Farebrother, J., Machado, M.C., Bowling, M.: Generalization and regularization in DQN. arXiv preprint arXiv:1810.00123 (2018)"},{"key":"34_CR5","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., et al.: Autoaugment: learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"34_CR7","unstructured":"Cobbe, K., et al.: Quantifying generalization in reinforcement learning. In: International Conference on Machine Learning. PMLR (2019)"},{"key":"34_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-11814-2_1","volume-title":"Adaptive and Learning Agents","author":"M Ponsen","year":"2010","unstructured":"Ponsen, M., Taylor, M.E., Tuyls, K.: Abstraction and generalization in reinforcement learning: a summary and framework. In: Taylor, M.E., Tuyls, K. (eds.) ALA 2009. LNCS (LNAI), vol. 5924, pp. 1\u201332. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-11814-2_1"},{"key":"34_CR9","unstructured":"Ghosh, D., Rahme, J., Kumar, A., et al.: Why generalization in RL is difficult: epistemic pomdps and implicit partial observability. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"34_CR10","unstructured":"Kirk, R., et al.: A survey of generalisation in deep reinforcement learning. arXiv preprint arXiv:2111.09794 (2021)"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Shanthamallu, U.S., et al.: A brief survey of machine learning methods and their sensor and IoT applications. In: 2017 8th International Conference on Information, Intelligence, Systems and Applications (IISA). IEEE (2017)","DOI":"10.1109\/IISA.2017.8316459"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Tobin, J., et al.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Bellemare, M.G., et al.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","DOI":"10.1613\/jair.3912"},{"key":"34_CR14","unstructured":"Zhang, A., Ballas, N., Pineau, J.: A dissection of overfitting and generalization in continuous reinforcement learning. arXiv, abs\/1806.07937 (2018)"},{"key":"34_CR15","unstructured":"Liu, Z., Li, X., Kang, B., Darrell, T.: Regularization matters in policy optimization - an empirical study on continuous control. arXiv: Learning (2020)"},{"issue":"5","key":"34_CR16","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1287\/opre.21.5.1071","volume":"21","author":"RD Smallwood","year":"1973","unstructured":"Smallwood, R.D., Sondik, E.J.: The optimal control of partially observable Markov processes over a finite horizon. Oper. Res. 21(5), 1071\u20131088 (1973)","journal-title":"Oper. Res."},{"key":"34_CR17","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable MDPS. arXiv preprint arXiv:1507.06527 (2015)"},{"key":"34_CR18","unstructured":"Zhu, P., Li, X., Poupart, P., Miao, G.: On improving deep reinforcement learning for pomdps. arXiv preprint arXiv:1704.07978 (2017)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Qureshi, A.H., et al.: Robot gains social intelligence through multimodal deep reinforcement learning. In: 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids). IEEE (2016)","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"key":"34_CR20","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1613\/jair.2078","volume":"27","author":"J Pineau","year":"2006","unstructured":"Pineau, J., Gordon, G., Thrun, S.: Anytime point-based approximations for large POMDPs. J. Artif. Intell. Res. 27, 335\u2013380 (2006)","journal-title":"J. Artif. Intell. Res."},{"issue":"3","key":"34_CR21","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/s10458-009-9103-z","volume":"21","author":"C Amato","year":"2010","unstructured":"Amato, C., Bernstein, D.S., Zilberstein, S.: Optimizing fixed-size stochastic controllers for POMDPs and decentralized POMDPs. Auton. Agent. Multi-Agent Syst. 21(3), 293\u2013320 (2010)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"34_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1613\/jair.1496","volume":"23","author":"N Roy","year":"2005","unstructured":"Roy, N., Gordon, G., Thrun, S.: Finding approximate POMDP solutions through belief compression. J. Artif. Intell. Res. 23, 1\u201340 (2005)","journal-title":"J. Artif. Intell. Res."},{"key":"34_CR23","unstructured":"Ramachandran, D., Amir, E.: Bayesian inverse reinforcement learning. In: IJCAI (2007)"},{"key":"34_CR24","unstructured":"Lazaric, A., Ghavamzadeh, M.: Bayesian multi-task reinforcement learning. In: ICML (2010)"},{"key":"34_CR25","unstructured":"Ghavamzadeh, M., et al.: Bayesian reinforcement learning: a survey. Found. Trends\u00ae Mach. Learn. 8(5-6), 359\u2013483 (2015)"},{"key":"34_CR26","unstructured":"Zhou, W., Pinto, L., Gupta, A.: Environment probing interaction policies. In: ICLR (2019)"},{"key":"34_CR27","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning (ICML) (2016)"},{"key":"34_CR28","unstructured":"Schulman, J., Abbeel, P., Chen, X.: Equivalence between policy gradients and soft Q-Learning. arXiv:1704.06440 (2017)"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: IROS (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"34_CR30","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30105-6_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T20:36:32Z","timestamp":1681331792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30105-6_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031301049","9783031301056"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30105-6_34","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":"13 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}