{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T02:49:41Z","timestamp":1742957381814,"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_22","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:02:55Z","timestamp":1726491775000},"page":"325-339","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Asymmetric Actor-Critic for\u00a0Adapting to\u00a0Changing Environments in\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Wangyang","family":"Yue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaochuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minne","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zunlin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Kou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Silver, D, et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u20139 (2016)","DOI":"10.1038\/nature16961"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u201333 (2015)","DOI":"10.1038\/nature14236"},{"key":"22_CR3","unstructured":"Filos, A., Tigkas, P., McAllister, R., Rhinehart, N., Levine, S., Gal, Y.: Can autonomous vehicles identify, recover from, and adapt to distribution shifts? In: International Conference on Machine Learning, pp. 3145\u20133153. PMLR (2020)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Smith, L., et al.: Demonstrating a walk in the park: learning to walk in 20 minutes with model-free reinforcement learning. Robotics: Science and Systems (2023)","DOI":"10.15607\/RSS.2023.XIX.056"},{"key":"22_CR5","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"},{"issue":"9","key":"22_CR6","doi-asserted-by":"publisher","first-page":"999","DOI":"10.3390\/electronics10090999","volume":"10","author":"AT Azar","year":"2021","unstructured":"Azar, A.T., et al.: Drone deep reinforcement learning: a review. Electronics 10(9), 999 (2021)","journal-title":"Electronics"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Kumar, A., Fu, Z., Pathak, D., Malik, J.: RMA: rapid motor adaptation for legged robots. arXiv preprint arXiv:2107.04034 (2021)","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"22_CR8","unstructured":"Benjamins, C., et al.:. Carl: A benchmark for contextual and adaptive reinforcement learning. arXiv preprint arXiv:2110.02102 (2021)"},{"key":"22_CR9","unstructured":"Kirk, R., Zhang, A., Grefenstette, E., Rockt\u00e4schel, T.: A survey of generalisation in deep reinforcement learning. arXiv preprint arXiv:2111.09794 (2021)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning quadrupedal locomotion over challenging terrain. Sci. Rob. 5(47), eabc5986 (2020)","DOI":"10.1126\/scirobotics.abc5986"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: 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), pp. 23\u201330. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"22_CR12","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 arXiv:1702.02453 (2017)","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Pinto, L., Andrychowicz, M., Welinder, P., Zaremba, W., Abbeel, P.: Asymmetric actor critic for image-based robot learning. arXiv preprint arXiv:1710.06542 (2017)","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"22_CR14","unstructured":"Hallak, A., Di Castro, D., Mannor, S.: Contextual Markov decision processes. arXiv preprint arXiv:1502.02259 (2015)"},{"key":"22_CR15","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: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 3803\u20133810. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Tan, J., et al.: Sim-to-real: learning agile locomotion for quadruped robots. arXiv preprint arXiv:1804.10332 (2018)","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Yang, R., Yang, G., Wang, X.: Neural volumetric memory for visual locomotion control. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1430\u20131440 (2023)","DOI":"10.1109\/CVPR52729.2023.00144"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Miki, T., Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning robust perceptive locomotion for quadrupedal robots in the wild. Sci. Rob. 7(62), eabk2822 (2022)","DOI":"10.1126\/scirobotics.abk2822"},{"key":"22_CR19","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. Adv. Neural Inf. Process. Syst. 12 (1999)"},{"key":"22_CR20","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304 . PMLR (2018)"},{"key":"22_CR21","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. Adv. Neural Inf. Process. Syst. 12 (1999)"},{"key":"22_CR22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F.A., Amato, C.: A Concise Introduction to Decentralized POMDPs. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28929-8"},{"key":"22_CR23","unstructured":"Baisero, A., Amato, C.: Unbiased asymmetric actor-critic for partially observable reinforcement learning. arXiv preprint arXiv:2105.11674 (2021)"},{"key":"22_CR24","unstructured":"Chen, D., Zhou, B., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning by cheating. In: Conference on Robot Learning, pp. 66\u201375. PMLR (2020)"},{"key":"22_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"22_CR26","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. InInternational conference on machine learning 2018 Jul 3 (pp. 1861-1870). PMLR"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Berndt, J.: JSBSim: an open source flight dynamics model in C++. In: AIAA Modeling and Simulation Technologies Conference and Exhibit, p. 4923 (2004)","DOI":"10.2514\/6.2004-4923"},{"key":"22_CR28","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Hwangbo, J., et al.: Learning agile and dynamic motor skills for legged robots. Sci. Rob. 4(26), eaau5872 (2019)","DOI":"10.1126\/scirobotics.aau5872"}],"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_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:12:55Z","timestamp":1726492375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72341-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723407","9783031723414"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72341-4_22","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"}}]}}