{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T05:57:22Z","timestamp":1761631042200},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191774","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"01-06","source":"Crossref","is-referenced-by-count":3,"title":["Elastic step DDPG: Multi-step reinforcement learning for improved sample efficiency"],"prefix":"10.1109","author":[{"given":"Adrian","family":"Ly","sequence":"first","affiliation":[{"name":"School of Information Technology, Deakin University,Geelong,Australia"}]},{"given":"Richard","family":"Dazeley","sequence":"additional","affiliation":[{"name":"School of Information Technology, Deakin University,Geelong,Australia"}]},{"given":"Peter","family":"Vamplew","sequence":"additional","affiliation":[{"name":"Federation University,Centre for Smart Analytics,Ballarat,Australia"}]},{"given":"Francisco","family":"Cruz","sequence":"additional","affiliation":[{"name":"University of New South Wales,Computer Science and Engineering,Sydney,Australia"}]},{"given":"Sunil","family":"Aryal","sequence":"additional","affiliation":[{"name":"School of Information Technology, Deakin University,Geelong,Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/820"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"volume-title":"Reinforcement learning: An intro-duction","year":"2018","author":"Sutton","key":"ref4"},{"key":"ref5","first-page":"3061","article-title":"Revisiting fundamentals of experience replay","volume-title":"International Conference on Machine Learning","author":"Fedus","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref7","first-page":"1373","article-title":"Revisiting rainbow: Promoting more insightful and inclusive deep reinforcement learning research","volume-title":"International Conference on Machine Learning","author":"Ceron","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127170"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref10","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"key":"ref12","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"176","article-title":"Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Anschel","year":"2017"},{"key":"ref14","article-title":"Maxmin q-learning: Controlling the estimation bias of q-learning","author":"Lan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413027"},{"key":"ref16","article-title":"Mixture of Step Returns in Bootstrapped DQN","author":"Chiang","year":"2020","journal-title":"arXiv preprint"},{"journal-title":"Adaptive N-step Boot-strapping with Off-policy Data","year":"2020","author":"Wang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/11556114_22"},{"key":"ref19","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108872"},{"journal-title":"Mushroomrl: Simplifying reinforcement learning research","year":"2021","author":"DEramo","key":"ref21"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver","year":"2014"},{"journal-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","year":"2016","author":"Coumans","key":"ref24"},{"key":"ref25","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5220\/0010227301070118"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-SmartCity-DSS50907.2020.00131"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191774.pdf?arnumber=10191774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T15:29:05Z","timestamp":1709306945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191774","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}