{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:52:53Z","timestamp":1775065973099,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000155","name":"SSHRC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000155","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9413027","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"347-353","source":"Crossref","is-referenced-by-count":18,"title":["The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lingheng","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rob","family":"Gorbet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dana","family":"Kulic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","author":"coumans","year":"2016","journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning"},{"key":"ref10","author":"horgan","year":"2018","journal-title":"Distributed prioritized experience replay"},{"key":"ref11","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref13","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proceedings of the 1993 Connectionist Models Summer School Hillsdale"},{"key":"ref14","author":"fujimoto","year":"2018","journal-title":"Addressing Function Approximation Error in Actor-Critic Methods"},{"key":"ref15","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref16","article-title":"Multi-step reinforcement learning: A unifying algorithm","author":"de asis","year":"0","journal-title":"Thirty-Second AAAI Conf Artif Intell"},{"key":"ref17","author":"van seijen","year":"2016","journal-title":"Effective multi-step temporal-difference learning for non-linear function approximation"},{"key":"ref18","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"0","journal-title":"Thirty-Second AAAI Conf Artif Intell"},{"key":"ref19","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref28","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor"},{"key":"ref4","author":"irpan","year":"2018","journal-title":"Deep reinforcement learning doesn't work yet"},{"key":"ref27","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref6","author":"meng","year":"2019","journal-title":"Learning to engage with interactive systems A field study"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref8","article-title":"World models","author":"ha","year":"2018","journal-title":"arXiv preprint arXiv 1803 10122"},{"key":"ref7","author":"plappert","year":"2017","journal-title":"Parameter space noise for exploration"},{"key":"ref2","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref9","author":"schaul","year":"2015","journal-title":"Prioritized experience replay"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref22","author":"feinberg","year":"2018","journal-title":"Model-based value estimation for efficient model-free reinforcement learning"},{"key":"ref21","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"0","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref24","first-page":"176","article-title":"Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning- Volume 70 JMLR org"},{"key":"ref23","first-page":"8224","article-title":"Sample- efficient reinforcement learning with stochastic ensemble value expansion","author":"buckman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","author":"silver","year":"2014","journal-title":"Deterministic policy gradient algorithms"},{"key":"ref25","author":"hernandez-garcia","year":"2019","journal-title":"Understanding multi-step deep reinforcement learning A systematic study of the DQN target"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09413027.pdf?arnumber=9413027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:45Z","timestamp":1652197245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9413027","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}