{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:47:49Z","timestamp":1763729269160,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543663","type":"print"},{"value":"9789819543670","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4367-0_42","type":"book-chapter","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:38:14Z","timestamp":1763728694000},"page":"625-639","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bayesian Uncertainty Estimation for\u00a0Targeted Counterfactual Experience Generation in\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6267-4903","authenticated-orcid":false,"given":"Lian","family":"Tong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8495-417X","authenticated-orcid":false,"given":"Yongjun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6815-3754","authenticated-orcid":false,"given":"Xiaoyu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1463-4165","authenticated-orcid":false,"given":"Zhiqiang","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Cao, H., Feng, F., Yang, T., Huo, J., Gao, Y.: Causal information prioritization for efficient reinforcement learning. arXiv preprint arXiv:2502.10097 (2025)","DOI":"10.1007\/s11432-024-4396-3"},{"key":"42_CR2","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, vol. 31 (2018)"},{"key":"42_CR3","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":"42_CR4","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"issue":"3","key":"42_CR5","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10994-021-05946-3","volume":"110","author":"E H\u00fcllermeier","year":"2021","unstructured":"H\u00fcllermeier, E., Waegeman, W.: Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach. Learn. 110(3), 457\u2013506 (2021)","journal-title":"Mach. Learn."},{"key":"42_CR6","unstructured":"Janner, M., Fu, J., Zhang, M., Levine, S.: When to trust your model: model-based policy optimization. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"42_CR7","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: Curl: contrastive unsupervised representations for reinforcement learning. In: International Conference on Machine Learning, pp. 5639\u20135650. PMLR (2020)"},{"key":"42_CR8","first-page":"19884","volume":"33","author":"M Laskin","year":"2020","unstructured":"Laskin, M., Lee, K., Stooke, A., Pinto, L., Abbeel, P., Srinivas, A.: Reinforcement learning with augmented data. Adv. Neural. Inf. Process. Syst. 33, 19884\u201319895 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"42_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130017","volume":"637","author":"S Lee","year":"2025","unstructured":"Lee, S., Gong, Y., Deng, C.: Counterfactual experience augmented off-policy reinforcement learning. Neurocomputing 637, 130017 (2025)","journal-title":"Neurocomputing"},{"key":"42_CR10","unstructured":"Leurent, E.: An environment for autonomous driving decision-making (2018). https:\/\/github.com\/eleurent\/highway-env"},{"key":"42_CR11","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Lockwood, O., Si, M.: A review of uncertainty for deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol.\u00a018, pp. 155\u2013162 (2022)","DOI":"10.1609\/aiide.v18i1.21959"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Lopez, P.A., et al.: Microscopic traffic simulation using sumo. In: The 21st IEEE International Conference on Intelligent Transportation Systems. IEEE (2018). https:\/\/elib.dlr.de\/124092\/","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"L\u00fctjens, B., Everett, M., How, J.P.: Safe reinforcement learning with model uncertainty estimates. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 8662\u20138668. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Madaan, N., Padhi, I., Panwar, N., Saha, D.: Generate your counterfactuals: towards controlled counterfactual generation for text. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 13516\u201313524 (2021)","DOI":"10.1609\/aaai.v35i15.17594"},{"key":"42_CR16","unstructured":"Mai, V., Mani, K., Paull, L.: Sample efficient deep reinforcement learning via uncertainty estimation. arXiv preprint arXiv:2201.01666 (2022)"},{"key":"42_CR17","first-page":"18143","volume":"35","author":"S Pitis","year":"2022","unstructured":"Pitis, S., Creager, E., Mandlekar, A., Garg, A.: Mocoda: model-based counterfactual data augmentation. Adv. Neural. Inf. Process. Syst. 35, 18143\u201318156 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"42_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"42_CR19","unstructured":"Sun, Y., Zhang, J., Jia, C., Lin, H., Ye, J., Yu, Y.: Model-bellman inconsistency for model-based offline reinforcement learning. In: International Conference on Machine Learning, pp. 33177\u201333194. PMLR (2023)"},{"key":"42_CR20","first-page":"43729","volume":"36","author":"Z Sun","year":"2023","unstructured":"Sun, Z., He, B., Liu, J., Chen, X., Ma, C., Zhang, S.: Offline imitation learning with variational counterfactual reasoning. Adv. Neural. Inf. Process. Syst. 36, 43729\u201343741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"42_CR21","unstructured":"Urp\u00ed, N.A., Bagatella, M., Vlastelica, M., Martius, G.: Causal action influence aware counterfactual data augmentation. arXiv preprint arXiv:2405.18917 (2024)"},{"key":"42_CR22","unstructured":"Wimmer, L., Sale, Y., Hofman, P., Bischl, B., H\u00fcllermeier, E.: Quantifying aleatoric and epistemic uncertainty in machine learning: are conditional entropy and mutual information appropriate measures? In: Uncertainty in Artificial Intelligence, pp. 2282\u20132292. PMLR (2023)"},{"key":"42_CR23","unstructured":"Yarats, D., Kostrikov, I., Fergus, R.: Image augmentation is all you need: regularizing deep reinforcement learning from pixels. In: International Conference on Learning Representations (2021)"},{"key":"42_CR24","unstructured":"Zhao, Y., Zhao, W., Boney, R., Kannala, J., Pajarinen, J.: Simplified temporal consistency reinforcement learning. In: International Conference on Machine Learning, pp. 42227\u201342246. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4367-0_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:38:24Z","timestamp":1763728704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4367-0_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"ISBN":["9789819543663","9789819543670"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4367-0_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"22 November 2025","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":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}