{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T12:52:20Z","timestamp":1766753540711,"version":"3.37.3"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tnnls.2021.3140042","type":"journal-article","created":{"date-parts":[[2022,1,18]],"date-time":"2022-01-18T22:02:08Z","timestamp":1642543328000},"page":"8086-8093","source":"Crossref","is-referenced-by-count":8,"title":["Self-Punishment and Reward Backfill for Deep <i>Q<\/i>-Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0061-4902","authenticated-orcid":false,"given":"Mohammad Reza","family":"Bonyadi","sequence":"first","affiliation":[{"name":"Microsoft Development Center Norway (MDCN), Trondheim, Norway"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Turnto Health, Brisbane, QLD, Australia"}]},{"given":"Maryam","family":"Ziaei","sequence":"additional","affiliation":[{"name":"Kavli Institute for Systems Neuroscience and Jebsen Centre for Alzheimer&#x2019;s Disease, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref12","first-page":"1","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref14","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref16","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017","journal-title":"arXiv 1707 08817"},{"key":"ref19","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"Proc ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11741"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207388"},{"key":"ref26","first-page":"9549","article-title":"Reinforcement learning with multiple experts: A Bayesian model combination approach","author":"gimelfarb","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref25","article-title":"Reward shaping via meta-learning","author":"zou","year":"2019","journal-title":"arXiv 1901 09330"},{"article-title":"Shaping and policy search in reinforcement learning","year":"2003","author":"ng","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref27","first-page":"11315","article-title":"Neural temporal-difference learning converges to global optima","volume":"32","author":"cai","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Don&#x2019;t Shoot the Dog The Art of Teaching and Training","year":"1999","author":"pryor","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican1251-26"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50035-0"},{"key":"ref4","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref3","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":"ref6","first-page":"1131","article-title":"Reconciling $\\lambda$\n-returns with experience replay","author":"daley","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref5"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10273172\/09684494.pdf?arnumber=9684494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:16:23Z","timestamp":1698084983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9684494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":27,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3140042","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}