{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:29:55Z","timestamp":1757543395152,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723407"},{"type":"electronic","value":"9783031723414"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72341-4_25","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:02:55Z","timestamp":1726491775000},"page":"369-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dual Action Policy for\u00a0Robust Sim-to-Real Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Ng Wen Zheng","family":"Terence","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Jianda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"25_CR1","unstructured":"An, G., Moon, S., Kim, J.H., Song, H.O.: Uncertainty-based offline reinforcement learning with diversified q-ensemble. NeurIPS (2021)"},{"key":"25_CR2","unstructured":"Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: ICML (2015)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Charpentier, A., Elie, R., Remlinger, C.: Reinforcement learning in economics and finance. Comput. Econ. (2021)","DOI":"10.1007\/s10614-021-10119-4"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chebotar, Y., et al.: Closing the sim-to-real loop: adapting simulation randomization with real world experience. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"25_CR5","unstructured":"Christiano, P.F., et al.: Transfer from simulation to real world through learning deep inverse dynamics model. arXiv preprint (2016)"},{"key":"25_CR6","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. NeurIPS (2018)"},{"key":"25_CR7","unstructured":"Desai, S., Durugkar, I., Karnan, H., Warnell, G., Hanna, J., Stone, P.: An imitation from observation approach to transfer learning with dynamics mismatch. NeurIPS (2020)"},{"key":"25_CR8","unstructured":"Eysenbach, B., Chaudhari, S., Asawa, S., Levine, S., Salakhutdinov, R.: Off-dynamics reinforcement learning: training for transfer with domain classifiers. In: ICLR (2020)"},{"key":"25_CR9","unstructured":"Ghasemipour, K., Gu, S.S., Nachum, O.: Why so pessimistic? Estimating uncertainties for offline RL through ensembles, and why their independence matters. NeurIPS (2022)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"25_CR11","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. In: ICML, pp. 1352\u20131361. PMLR (2017)"},{"key":"25_CR12","unstructured":"Haarnoja, T., et\u00a0al.: Soft actor-critic algorithms and applications. arXiv preprint (2018)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Hanna, J., Stone, P.: Grounded action transformation for robot learning in simulation. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11124"},{"key":"25_CR14","unstructured":"Janner, M., Fu, J., Zhang, M., Levine, S.: When to trust your model: Model-based policy optimization. NeurIPS (2019)"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhang, T., Ho, D., Bai, Y., Liu, C.K., Levine, S., Tan, J.: Simgan: hybrid simulator identification for domain adaptation via adversarial reinforcement learning. In: ICRA (2021)","DOI":"10.1109\/ICRA48506.2021.9561731"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Karnan, H., Desai, S., Hanna, J.P., Warnell, G., Stone, P.: Reinforced grounded action transformation for sim-to-real transfer. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341149"},{"key":"25_CR17","unstructured":"Kurutach, T., Clavera, I., Duan, Y., Tamar, A., Abbeel, P.: Model-ensemble trust-region policy optimization. In: ICLR (2018)"},{"key":"25_CR18","unstructured":"Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. NeurIPS (2017)"},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning quadrupedal locomotion over challenging terrain. Sci. Robot. (2020)","DOI":"10.1126\/scirobotics.abc5986"},{"key":"25_CR20","unstructured":"Liang, X., Shu, K., Lee, K., Abbeel, P.: Reward uncertainty for exploration in preference-based reinforcement learning. In: Deep RL Workshop NeurIPS 2021 (2021)"},{"key":"25_CR21","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint (2015)"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., See, K.C., Ngiam, K.Y., Celi, L.A., Sun, X., Feng, M.: Reinforcement learning for clinical decision support in critical care: comprehensive review. J. Med. Internet Res. (2020)","DOI":"10.2196\/preprints.18477"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Mnih, V., et\u00a0al.: Human-level control through deep reinforcement learning. Nature (2015)","DOI":"10.1038\/nature14236"},{"key":"25_CR24","unstructured":"Niu, H., et\u00a0al.: When to trust your simulator: dynamics-aware hybrid offline-and-online reinforcement learning. NeurIPS (2022)"},{"key":"25_CR25","unstructured":"Osband, I., Blundell, C., Pritzel, A., Van\u00a0Roy, B.: Deep exploration via bootstrapped DQN. NeurIPS (2016)"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: ICRA (2018)","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"25_CR27","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction, MIT press (2018)"},{"key":"25_CR28","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":"25_CR29","doi-asserted-by":"crossref","unstructured":"Yu, W., Tan, J., Liu, C.K., Turk, G.: Preparing for the unknown: learning a universal policy with online system identification. arXiv preprint (2017)","DOI":"10.15607\/RSS.2017.XIII.048"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72341-4_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:13:27Z","timestamp":1726492407000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72341-4_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723407","9783031723414"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72341-4_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}