{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:48:09Z","timestamp":1782992889884,"version":"3.54.5"},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642006432","type":"print"},{"value":"9783642006449","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-00644-9_33","type":"book-chapter","created":{"date-parts":[[2009,5,14]],"date-time":"2009-05-14T09:37:49Z","timestamp":1242293869000},"page":"367-378","source":"Crossref","is-referenced-by-count":13,"title":["Efficient Distributed Reinforcement Learning through Agreement"],"prefix":"10.1007","author":[{"given":"Paulina","family":"Varshavskaya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leslie Pack","family":"Kaelbling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"33_CR1","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/S0954-1810(01)00028-0","volume":"15","author":"J. Baxter","year":"2001","unstructured":"Baxter, J., Bartlett, P.L.: Infinite-horizon gradient-based policy search. J. of Artificial Intelligence Res.\u00a015, 319\u2013350 (2001)","journal-title":"J. of Artificial Intelligence Res."},{"key":"33_CR2","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and Distributed Computation: Numerical Methods. Athena Scientific (1997)"},{"key":"33_CR3","unstructured":"Chang, Y.-H., Ho, T., Kaelbling, L.P.: All learning is local: Multi-agent learning in global reward games. In: Advances in Neural Information Processing Systems, vol.\u00a016 (2004)"},{"issue":"4","key":"33_CR4","first-page":"217","volume":"16","author":"F. Fernandez","year":"2001","unstructured":"Fernandez, F., Parker, L.E.: Learning in large cooperative multi-robot domains. Int. J. of Robotics and Automation\u00a016(4), 217\u2013226 (2001)","journal-title":"Int. J. of Robotics and Automation"},{"key":"33_CR5","unstructured":"Guestrin, C., Koller, D., Parr, R.: Multiagent planning with factored MDPs. In: Advances in Neural Information Processing Systems, vol.\u00a014 (2002)"},{"key":"33_CR6","unstructured":"Hu, J., Wellman, M.P.: Multiagent reinforcement learning: Theoretical framework and an algorithm. In: Proc. Int. Conf. on Machine Learning, pp. 242\u2013250 (1998)"},{"key":"33_CR7","first-page":"1789","volume":"7","author":"J.R. Kok","year":"2006","unstructured":"Kok, J.R., Vlassis, N.: Collaborative multiagent reinforcement learning by payoff propagation. J. of Machine Learning Res.\u00a07, 1789\u20131828 (2006)","journal-title":"J. of Machine Learning Res."},{"issue":"3","key":"33_CR8","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TRO.2008.921567","volume":"24","author":"K.M. Lynch","year":"2008","unstructured":"Lynch, K.M., Schwartz, I.B., Yang, P., Freeman, R.: Decentralized environmental modeling by mobile sensor networks. IEEE Trans. on Robotics\u00a024(3), 710\u2013724 (2008)","journal-title":"IEEE Trans. on Robotics"},{"issue":"1","key":"33_CR9","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1023\/A:1008819414322","volume":"4","author":"M.J. Matari\u0107","year":"1997","unstructured":"Matari\u0107, M.J.: Reinforcement learning in the multi-robot domain. Autonomous Robots\u00a04(1), 73\u201383 (1997)","journal-title":"Autonomous Robots"},{"key":"33_CR10","unstructured":"Moallemi, C.C., Van Roy, B.: Distributed optimization in adaptive networks. In: Advances in Neural Information Processing Systems, vol.\u00a015 (2003)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Moallemi, C.C., Van Roy, B.: Consensus propagation. IEEE Trans. on Information Theory\u00a052(11) (2006)","DOI":"10.1109\/TIT.2006.883539"},{"key":"33_CR12","unstructured":"Peshkin, L.: Reinforcement Learning by Policy Search. PhD thesis, Brown University (2001)"},{"key":"33_CR13","unstructured":"Schneider, J., Wong, W.-K., Moore, A., Riedmiller, M.: Distributed value functions. In: Proc. Int. Conf. on Machine Leanring (1999)"},{"issue":"9","key":"33_CR14","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1109\/TAC.1986.1104412","volume":"AC-31","author":"J.N. Tsitsiklis","year":"1986","unstructured":"Tsitsiklis, J.N., Bertsekas, D.P., Athans, M.: Distributed asynchronous deterministic and stochastic gradient optimization algorithms. IEEE Trans. on Automatic Control\u00a0AC-31(9), 803\u2013812 (1986)","journal-title":"IEEE Trans. on Automatic Control"},{"key":"33_CR15","unstructured":"Varshavskaya, P., Kaelbling, L.P., Rus, D.: Distributed learning for modular robots. In: Proc. Int. Conf. on Robots and Systems (2004)"},{"issue":"3\u20134","key":"33_CR16","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1177\/0278364907084983","volume":"27","author":"P. Varshavskaya","year":"2008","unstructured":"Varshavskaya, P., Kaelbling, L.P., Rus, D.: Automated design of adaptive controllers for modular robots using reinforcement learning. Int. J. of Robotics Res.\u00a027(3\u20134), 505\u2013526 (2008)","journal-title":"Int. J. of Robotics Res."}],"container-title":["Distributed Autonomous Robotic Systems 8"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-00644-9_33.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T09:46:39Z","timestamp":1619775999000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-00644-9_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642006432","9783642006449"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-00644-9_33","relation":{},"subject":[],"published":{"date-parts":[[2009]]}}}