{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:00:21Z","timestamp":1776056421977,"version":"3.50.1"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government (MSIT) (Development of Robot Hand Manipulation Intelligence to Learn Methods and Procedures for Handling Various Objects with Tactile Robot Hands)","award":["2018-0-00677"],"award-info":[{"award-number":["2018-0-00677"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2936863","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T16:18:45Z","timestamp":1566490725000},"page":"118776-118791","source":"Crossref","is-referenced-by-count":45,"title":["Rewards Prediction-Based Credit Assignment for Reinforcement Learning With Sparse Binary Rewards"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0841-5190","authenticated-orcid":false,"given":"Minah","family":"Seo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luiz Felipe","family":"Vecchietti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6918-124X","authenticated-orcid":false,"given":"Sangkeum","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6949-1739","authenticated-orcid":false,"given":"Dongsoo","family":"Har","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning to play in a day: Faster deep reinforcement learning by optimality tightening","author":"he","year":"2016","journal-title":"arXiv 1611 01606"},{"key":"ref11","first-page":"1","article-title":"The influence of reward on the speed of reinforcement learning: An analysis of shaping","author":"laud","year":"2003","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932257"},{"key":"ref13","first-page":"355","article-title":"Reinforcement learning and shaping: Encouraging intended behaviors","author":"laud","year":"2002","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878894"},{"key":"ref15","first-page":"1","article-title":"Belief reward shaping in reinforcement learning","author":"marom","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273572"},{"key":"ref17","first-page":"5396","article-title":"Hybrid reward architecture for reinforcement learning","author":"van seijen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1001"},{"key":"ref19","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref4","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"arXiv 1712 01815"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref8","article-title":"Temporal credit assignment in reinforcement learning","author":"sutton","year":"1984"},{"key":"ref7","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"arXiv 1703 02949"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"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":"1","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref21","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref24","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"arXiv 1802 09464"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref26","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08809762.pdf?arnumber=8809762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:31:06Z","timestamp":1641987066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8809762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2936863","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}