{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T05:45:57Z","timestamp":1729662357780,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,8]]},"DOI":"10.1109\/ijcnn.2013.6706982","type":"proceedings-article","created":{"date-parts":[[2014,1,10]],"date-time":"2014-01-10T15:08:44Z","timestamp":1389366524000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["On the convergence of techniques that improve value iteration"],"prefix":"10.1109","author":[{"given":"Marek","family":"Grzes","sequence":"first","affiliation":[]},{"given":"Jesse","family":"Hoey","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","article-title":"Asynchronous modified policy iteration with single-sided updates","author":"singh","year":"1993","journal-title":"University of Massachusetts Technical Report"},{"key":"17","article-title":"Solving concurrent markov decision processes","author":"mausam","year":"2004","journal-title":"Proc Of AAAI"},{"journal-title":"Introduction to Algorithms","year":"2001","author":"cormen","key":"18"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"15"},{"key":"16","first-page":"213","article-title":"R-max - A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"JMLR"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.24.11.1127"},{"key":"14","article-title":"Efficient planning in r-max","author":"grzes","year":"2011","journal-title":"Proc of AAMAS"},{"key":"11","first-page":"12","article-title":"Labeled RTDP: Improving the convergence of real-time dynamic programming","author":"bonet","year":"2003","journal-title":"Proc ICA-03"},{"journal-title":"Dynamic Programming and Markov Processes","year":"1960","author":"howard","key":"12"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2007","author":"bertsekas","key":"21"},{"key":"20","article-title":"Heuristic search value iteration for POMDPs","author":"smith","year":"2004","journal-title":"Proc Of UAI"},{"key":"22","first-page":"851","article-title":"Prioritization methods for accelerating MDP solvers","volume":"6","author":"wingate","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"23","article-title":"Priorioritized sweeping converges to the optimal value function","author":"li","year":"2008","journal-title":"Rutgers University Tech Rep"},{"journal-title":"Artificial Intelligence A Modern Approach","year":"2002","author":"russell","key":"24"},{"key":"25","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc of ICML"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2010.5707073"},{"journal-title":"Parallel and Distributed Computation Numerical Methods","year":"1989","author":"bertsekas","key":"27"},{"journal-title":"Accelerating Successive Approximation Algorithm via Action Elimination","year":"2008","author":"jaber","key":"28"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993308"},{"key":"2","article-title":"Tight performance bounds on greedy policies based on imperfect value functions","author":"williams","year":"1993","journal-title":"Northeasterm University Tech Rep NU-CCS-93-14"},{"key":"10","first-page":"1860","article-title":"Topological value iteration algorithm for markov decision processes","author":"dai","year":"2007","journal-title":"Proc of IJCAI"},{"key":"1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"6","article-title":"Fast exact planning in markov decision processes","author":"mcmahan","year":"2005","journal-title":"Proc of ICAPS"},{"key":"5","first-page":"1001","article-title":"Generalized prioritized sweeping","author":"andre","year":"1997","journal-title":"Proc of NIPS"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"9","article-title":"Prioritizing bellman backups without a priority queue","author":"dai","year":"2007","journal-title":"Proc of ICAPS"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102423"}],"event":{"name":"2013 International Joint Conference on Neural Networks (IJCNN 2013 - Dallas)","start":{"date-parts":[[2013,8,4]]},"location":"Dallas, TX, USA","end":{"date-parts":[[2013,8,9]]}},"container-title":["The 2013 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6691896\/6706705\/06706982.pdf?arnumber=6706982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T21:09:33Z","timestamp":1647983373000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6706982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2013.6706982","relation":{},"subject":[],"published":{"date-parts":[[2013,8]]}}}