{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T22:30:34Z","timestamp":1773354634906,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031434235","type":"print"},{"value":"9783031434242","type":"electronic"}],"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\/978-3-031-43424-2_3","type":"book-chapter","created":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:37:24Z","timestamp":1694983044000},"page":"36-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Exploring the\u00a0Training Robustness of\u00a0Distributional Reinforcement Learning Against Noisy State Observations"],"prefix":"10.1007","author":[{"given":"Ke","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingnan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangling","family":"Jui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linglong","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"key":"3_CR1","unstructured":"Barth-Maron, G., et al.: Distributed distributional deterministic policy gradients. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"3_CR2","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: International Conference on Machine Learning (ICML) (2017)"},{"issue":"1","key":"3_CR3","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s42400-019-0027-x","volume":"2","author":"T Chen","year":"2019","unstructured":"Chen, T., Liu, J., Xiang, Y., Niu, W., Tong, E., Han, Z.: Adversarial attack and defense in reinforcement learning-from AI security view. Cybersecurity 2(1), 11 (2019)","journal-title":"Cybersecurity"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Dabney, W., Ostrovski, G., Silver, D., Munos, R.: Implicit quantile networks for distributional reinforcement learning. In: International Conference on Machine Learning (ICML) (2018)","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Dabney, W., Rowland, M., Bellemare, M.G., Munos, R.: Distributional reinforcement learning with quantile regression. In: Association for the Advancement of Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"3_CR6","unstructured":"Ghiassian, S., Patterson, A., Garg, S., Gupta, D., White, A., White, M.: Gradient temporal-difference learning with regularized corrections. In: International Conference on Machine Learning, pp. 3524\u20133534. PMLR (2020)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Guan, Z., et al.: Robust stochastic bandit algorithms under probabilistic unbounded adversarial attack. In: AAAI, pp. 4036\u20134043 (2020)","DOI":"10.1609\/aaai.v34i04.5821"},{"key":"3_CR8","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":"3_CR9","unstructured":"Huang, S., Papernot, N., Goodfellow, I., Duan, Y., Abbeel, P.: Adversarial attacks on neural network policies. In: International Conference on Learning Representations (ICLR) workshop (2017)"},{"key":"3_CR10","unstructured":"Ilahi, I., et al.: Challenges and countermeasures for adversarial attacks on deep reinforcement learning. arXiv preprint arXiv:2001.09684 (2020)"},{"key":"3_CR11","unstructured":"Imani, E., White, M.: Improving regression performance with distributional losses. In: International Conference on Machine Learning, pp. 2157\u20132166. PMLR (2018)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Lin, Y.C., et al.: Tactics of adversarial attack on deep reinforcement learning agents. arXiv preprint arXiv:1703.06748 (2017)","DOI":"10.24963\/ijcai.2017\/525"},{"key":"3_CR13","unstructured":"Ma, X., Xia, L., Zhou, Z., Yang, J., Zhao, Q.: DSAC: distributional soft actor critic for risk-sensitive reinforcement learning. arXiv preprint arXiv:2004.14547 (2020)"},{"key":"3_CR14","unstructured":"Mavrin, B., Zhang, S., Yao, H., Kong, L., Wu, K., Yu, Y.: Distributional reinforcement learning for efficient exploration. In: International Conference on Machine Learning (ICML) (2019)"},{"issue":"7540","key":"3_CR15","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\u2013533 (2015)","journal-title":"Nature"},{"key":"3_CR16","unstructured":"Nguyen, T.T., Gupta, S., Venkatesh, S.: Distributional reinforcement learning with maximum mean discrepancy. In: Association for the Advancement of Artificial Intelligence (AAAI) (2020)"},{"key":"3_CR17","unstructured":"Pattanaik, A., Tang, Z., Liu, S., Bommannan, G., Chowdhary, G.: Robust deep reinforcement learning with adversarial attacks. In: AAMAS (2018)"},{"key":"3_CR18","unstructured":"Shen, Q., Li, Y., Jiang, H., Wang, Z., Zhao, T.: Deep reinforcement learning with robust and smooth policy. In: International Conference on Machine Learning, pp. 8707\u20138718. PMLR (2020)"},{"key":"3_CR19","unstructured":"Singh, R., Zhang, Q., Chen, Y.: Improving robustness via risk averse distributional reinforcement learning. arXiv preprint arXiv:2005.00585 (2020)"},{"key":"3_CR20","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"3_CR21","unstructured":"Zhang, H., Chen, H., Xiao, C., Li, B., Boning, D., Hsieh, C.J.: Robust deep reinforcement learning against adversarial perturbations on observations. In: Advances in Neural Information Processing Systems (2020)"},{"key":"3_CR22","unstructured":"Zhang, S.: Modularized implementation of deep RL algorithms in PyTorch (2018). https:\/\/github.com\/ShangtongZhang\/DeepRL"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yao, H.: Quota: The quantile option architecture for reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5797\u20135804 (2019)","DOI":"10.1609\/aaai.v33i01.33015797"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43424-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:37:36Z","timestamp":1694983056000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43424-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434235","9783031434242"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43424-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","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":"196","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":"24% - 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":"3.63","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":"4.5","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":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted 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)"}}]}}