{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T05:35:25Z","timestamp":1729661725410,"version":"3.28.0"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,8]]},"DOI":"10.1109\/mmar.2015.7283925","type":"proceedings-article","created":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T17:48:57Z","timestamp":1443721737000},"page":"495-500","source":"Crossref","is-referenced-by-count":1,"title":["Sequence Q-learning: A memory-based method towards solving POMDP"],"prefix":"10.1109","author":[{"given":"Janis","family":"Zuters","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN.2010.5596811","article-title":"Region Enchanced Neural Q-learning for solving model-based POMDPs","author":"wiering","year":"2010","journal-title":"neural networks (IJCNN) The 2010 International Joint Conference on Neural Networks"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015346"},{"key":"ref12","article-title":"Using eligibility traces to find the best memoryless policy in partially observable Markov decision processes","author":"loch","year":"1998","journal-title":"Intl conf on Machine Learning"},{"key":"ref13","first-page":"585","article-title":"SarsaLandmark: An Algorithm for Learning in POMDPs with Land-marks","author":"james","year":"0","journal-title":"Proceedings of 8th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2009)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2009.04.002"},{"key":"ref3","first-page":"1047","article-title":"Hierarchical memory-based reinforcement learning","author":"hernandez-gardiol","year":"2001","journal-title":"Advances in Neural Information Processing Systems 13"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref6"},{"key":"ref5","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref8","volume":"101","author":"kaelbling","year":"1998","journal-title":"Planning and acting in partially observable stochastic domains Artificial Intelligence"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref7"},{"journal-title":"Instance-based state identification for reinforcement learning In Advances In Neural Information Processing Systems 7","year":"1995","author":"mccallum","key":"ref2"},{"key":"ref1","article-title":"Reinforcement learning for problems with hidden state","author":"hasinoff","year":"2003","journal-title":"Technical Report"},{"journal-title":"Metric state space reinforcement learning for a vision-capable mobile robot","year":"2003","author":"zhumatiy","key":"ref9"}],"event":{"name":"2015 20th International Conference on Methods and Models in Automation and Robotics (MMAR )","start":{"date-parts":[[2015,8,24]]},"location":"Miedzyzdroje, Poland","end":{"date-parts":[[2015,8,27]]}},"container-title":["2015 20th International Conference on Methods and Models in Automation and Robotics (MMAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7269329\/7283695\/07283925.pdf?arnumber=7283925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T16:36:51Z","timestamp":1498235811000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7283925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,8]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/mmar.2015.7283925","relation":{},"subject":[],"published":{"date-parts":[[2015,8]]}}}