{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T23:55:03Z","timestamp":1789862103210,"version":"4.0.1"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/ssci.2016.7849366","type":"proceedings-article","created":{"date-parts":[[2017,2,16]],"date-time":"2017-02-16T22:24:33Z","timestamp":1487283873000},"page":"1-8","source":"Crossref","is-referenced-by-count":82,"title":["Comparing exploration strategies for Q-learning in random stochastic mazes"],"prefix":"10.1109","author":[{"given":"Arryon D.","family":"Tijsma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madalina M.","family":"Drugan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco A.","family":"Wiering","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.4.447"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058926"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/21.21595"},{"key":"ref14","author":"schmidhuber","year":"1991","journal-title":"Adaptive Confidence and Adaptive Curiosity"},{"key":"ref15","first-page":"531","article-title":"Active exploration in dynamic environments","author":"thrun","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref17","article-title":"Algorithms for multi-armed bandit problems","author":"kuleshov","year":"2014","journal-title":"arXiv preprint arXiv 1402 6028"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SCIS-ISIS.2014.7044672"},{"key":"ref19","first-page":"760","author":"kennedy","year":"2011","journal-title":"Particle Swarm Optimization"},{"key":"ref4","author":"yahyaa","year":"2015","journal-title":"Explorations in reinforcement learning Online action selection and online value function approximation"},{"key":"ref3","article-title":"The role of exploration in learning control","author":"thrun","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref6","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref5","author":"wiering","year":"1999","journal-title":"Explorations in Efficient Reinforcement Learning"},{"key":"ref8","first-page":"437","article-title":"Multi-armed bandit algorithms and empirical evaluation","author":"vermorel","year":"2005","journal-title":"European Conference on Machine Learning"},{"key":"ref7","article-title":"Efficient exploration in reinforcement learning","author":"thrun","year":"1992","journal-title":"Tech Rep"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","author":"wiering","year":"2012","journal-title":"Reinforcement Learning State-of-the-Art"},{"key":"ref9","first-page":"223","article-title":"Efficient model-based exploration","author":"wiering","year":"1998","journal-title":"Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref21","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref26","author":"barto","year":"1991","journal-title":"Real-time learning and control using asynchronous dynamic programming"},{"key":"ref25","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"}],"event":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Athens, Greece","start":{"date-parts":[[2016,12,6]]},"end":{"date-parts":[[2016,12,9]]}},"container-title":["2016 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7840087\/7849361\/07849366.pdf?arnumber=7849366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,18]],"date-time":"2019-09-18T19:57:02Z","timestamp":1568836622000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7849366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ssci.2016.7849366","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}