{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T15:06:41Z","timestamp":1730214401951,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/devlrn.2019.8850685","type":"proceedings-article","created":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T23:40:48Z","timestamp":1569886848000},"page":"189-194","source":"Crossref","is-referenced-by-count":0,"title":["A Categorization of Reinforcement Learning Exploration Techniques which Facilitates Combination of Different Methods"],"prefix":"10.1109","author":[{"given":"Bjorn Ivar","family":"Teigen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai Olav","family":"Ellefsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jim","family":"Torresen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143949"},{"key":"ref11","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref12","first-page":"1889","article-title":"Trust Region Policy Optimization","volume":"37","author":"schulman","year":"2015","journal-title":"ICML'15 Proceedings of the 32nd International Conference on International Conference on Machine Learning"},{"key":"ref13","first-page":"4026","article-title":"Deep Exploration via Bootstrapped DQN","volume":"29","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"0","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref16","first-page":"6284","article-title":"Boltzmann Exploration Done Right","volume":"30","author":"cesa-bianchi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","volume":"12","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref18","first-page":"2613","article-title":"Double Q-learning","volume":"23","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"journal-title":"Parameter space noise for exploration","year":"0","author":"plappert","key":"ref3"},{"key":"ref6","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"0","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/09540090600768658"},{"journal-title":"Reinforcement Learning An Introduction","year":"2017","author":"sutton","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007541107674"},{"key":"ref2","volume":"7","author":"osband","year":"2015","journal-title":"Bootstrapped Thompson Sampling and Deep Exploration"},{"key":"ref1","first-page":"1109","article-title":"VIME: Variational Information Maximizing Exploration","volume":"5","author":"houthooft","year":"2016","journal-title":"Advances in Neural Information Processing Systems I (NIPS)"},{"key":"ref9","volume":"7","author":"stadie","year":"2015","journal-title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models"},{"key":"ref20","volume":"6","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"kirkpatrick","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"journal-title":"Efficient memory-based learning for robot control","year":"1990","author":"moore","key":"ref21"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/2200000070"}],"event":{"name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","start":{"date-parts":[[2019,8,19]]},"location":"Oslo, Norway","end":{"date-parts":[[2019,8,22]]}},"container-title":["2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8843356\/8850675\/08850685.pdf?arnumber=8850685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T17:49:40Z","timestamp":1658080180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8850685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2019.8850685","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}