{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:36:38Z","timestamp":1730208998359,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,7]]},"DOI":"10.1109\/coginf.2010.5599681","type":"proceedings-article","created":{"date-parts":[[2010,10,12]],"date-time":"2010-10-12T15:44:17Z","timestamp":1286898257000},"page":"530-535","source":"Crossref","is-referenced-by-count":9,"title":["Reinforcement learning for multi-agent patrol policy"],"prefix":"10.1109","author":[{"given":"Zhaohui","family":"Hu","sequence":"first","affiliation":[]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","article-title":"Distributed mobile autonomous agents in network management","author":"andrade","year":"2001","journal-title":"Proceedings of International Conference on Parallel and Distributed Processing Techniques and Applications"},{"key":"ref3","first-page":"113","article-title":"distributed neural network-based policy gradient reinforcement learning for multi-robot formations","author":"shang","year":"2008","journal-title":"Proceedings of the International Conference on Information and Automation"},{"key":"ref10","first-page":"279","volume":"8","author":"watkins","year":"1992","journal-title":"Q-learning Machine Learning"},{"key":"ref6","first-page":"1524","article-title":"A theoretical analysis of multi-agent patrolling strategies","volume":"3","author":"chevaleyre","year":"2004","journal-title":"Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref11","first-page":"47","article-title":"Reinforcement learning and its relationship to supervised learning","author":"barto","year":"2004","journal-title":"Handbook of Learning and Approximate Dynamic Programming"},{"key":"ref5","first-page":"1122","article-title":"Multi-agent patrolling with reinforcement learning","author":"santana","year":"2004","journal-title":"Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref12","first-page":"359","article-title":"Supervised actor-critic reinforcement learning","author":"rosenstein","year":"2004","journal-title":"Handbook of Learning and Approximate Dynamic Programming"},{"key":"ref8","first-page":"474","article-title":"Recent Advances on Multi-agent Patrolling","author":"almeida","year":"2004","journal-title":"SBIA 2004 LNAI 3171"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2009.125"},{"journal-title":"Multi-Agent System An Introduction to Distributed Artificial Intelligence","year":"1999","author":"ferber","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/367766.368168"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"}],"event":{"name":"2010 9th IEEE International Conference on Cognitive Informatics (ICCI)","start":{"date-parts":[[2010,7,7]]},"location":"Beijing, China","end":{"date-parts":[[2010,7,9]]}},"container-title":["9th IEEE International Conference on Cognitive Informatics (ICCI'10)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5560187\/5599672\/05599681.pdf?arnumber=5599681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,19]],"date-time":"2017-03-19T00:08:34Z","timestamp":1489882114000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5599681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,7]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/coginf.2010.5599681","relation":{},"subject":[],"published":{"date-parts":[[2010,7]]}}}