{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:23:33Z","timestamp":1791505413583,"version":"4.3.4"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030058159","type":"print"},{"value":"9783030058166","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05816-6_3","type":"book-chapter","created":{"date-parts":[[2019,1,29]],"date-time":"2019-01-29T14:42:46Z","timestamp":1548772966000},"page":"35-49","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["Distributed Reinforcement Learning for Multi-robot Decentralized Collective Construction"],"prefix":"10.1007","author":[{"given":"Guillaume","family":"Sartoretti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Paivine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T. K. Satish","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Koenig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Howie","family":"Choset","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,1,30]]},"reference":[{"key":"3_CR1","unstructured":"Buoniu, L., Babu\u0161ka, R., De Schutter, B., Srinivasan, D., Jain, L.C., Buoniu, L., Babu\u0161ka, R., De Schutter, B.: Multi-agent reinforcement learning: an overview. Stud. Comput. Intell. 310, 183\u2013221 (2010)"},{"key":"3_CR2","unstructured":"Cai, T., Zhang, D., Kumar, S., Koenig, S., Ayanian, N.: Local search on trees and a framework for automated construction using multiple identical robots [Short paper]. In: International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 1301\u20131302 (2016)"},{"key":"3_CR3","unstructured":"Foerster, J., Assael, I.A., de\u00a0Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2137\u20132145 (2016)"},{"key":"3_CR4","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent Policy Gradients (2017). arXiv:1705.08926"},{"key":"3_CR5","unstructured":"Guestrin, C., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: International Conference on Machine Learning, pp. 227\u2013234 (2002)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 66\u201383. Springer (2017)","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"3_CR7","unstructured":"Hausknecht, M., Stone, P.: Deep Recurrent Q-Learning for Partially Observable MDPs, vol. 7, no. 1 (2015). arxiv:1507.06527"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR9","unstructured":"Koenig, S., Kumar, S.: A case for collaborative construction as testbed for cooperative multi-agent planning. In: ICAPS-17 Scheduling and Planning Applications Workshop (2017)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Kumar, S., Jung, S., Koenig, S.: A tree-based algorithm for construction robots. In: International Conference on Automated Planning and Scheduling (2014)","DOI":"10.1609\/icaps.v24i1.13673"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Kumar, T.S., Jung, S.J., Koenig, S.: A tree-based algorithm for construction robots. In: International Conference on Automated Planning and Scheduling (2014)","DOI":"10.1609\/icaps.v24i1.13673"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Lample, G., Chaplot, D.S.: Playing FPS games with deep reinforcement learning. In: AAAI Conference on Artificial Intelligence, pp. 2140\u20132146 (2017)","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"3_CR13","unstructured":"Lau, Q.P., Lee, M.L., Hsu, W.: Coordination guided reinforcement learning. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 215\u2013222 (2012)"},{"key":"3_CR14","unstructured":"Le, H.M., Yue, Y., Carr, P.: Coordinated Multi-agent Imitation Learning (2017). arXiv:1703.03121"},{"key":"3_CR15","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, pp. 6382\u20136393 (2017)"},{"key":"3_CR16","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., Kavukcuoglu, K.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"3_CR17","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing Atari with Deep Reinforcement Learning (2013). arXiv:1312.5602"},{"key":"3_CR18","unstructured":"Neto, G.: From single-agent to multi-agent reinforcement learning: foundational concepts and methods. In: Learning Theory Course (2005)"},{"key":"3_CR19","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action-conditional video prediction using deep networks in Atari games. In: Advances in Neural Information Processing Systems, pp. 2863\u20132871 (2015)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Petersen, K., Nagpal, R., Werfel, J.: TERMES: an autonomous robotic system for three-dimensional collective construction. In: International Conference on Robotics: Science and Systems (2011)","DOI":"10.15607\/RSS.2011.VII.035"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Sartoretti, G., Shi, Y., Paivine, W., Travers, M., Choset, H.: Distributed learning for the decentralized control of articulated mobile robots. In: Accepted to ICRA 2018, Brisbane, Australia, 21\u201325 May 2018","DOI":"10.1109\/ICRA.2018.8460802"},{"key":"3_CR22","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized Experience Replay (2015). arXiv:1511.05952"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Schwartz, H.M.: Multi-agent Machine Learning: A Reinforcement Approach. Wiley (2014)","DOI":"10.1002\/9781118884614"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. 1998. In: A Bradford Book (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: AAAI Conference on Artificial Intelligence, pp. 2094\u20132100 (2016)","DOI":"10.1609\/aaai.v30i1.10295"}],"container-title":["Springer Proceedings in Advanced Robotics","Distributed Autonomous Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05816-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T04:02:36Z","timestamp":1694577756000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05816-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030058159","9783030058166"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05816-6_3","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"value":"2511-1256","type":"print"},{"value":"2511-1264","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"30 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}