{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:51:11Z","timestamp":1773247871580,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3090364","type":"journal-article","created":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T19:52:38Z","timestamp":1624045958000},"page":"97557-97568","source":"Crossref","is-referenced-by-count":19,"title":["Subgoal-Based Reward Shaping to Improve Efficiency in Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7218-7842","authenticated-orcid":false,"given":"Takato","family":"Okudo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5907-7382","authenticated-orcid":false,"given":"Seiji","family":"Yamada","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Reward shaping with dynamic trajectory aggregation","author":"okudo","year":"2021","journal-title":"Proc Int Joint Conf Neural Netw (IJCNN)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2010.01.001"},{"key":"ref33","first-page":"380","article-title":"Value function approximation in reinforcement learning using the Fourier basis","author":"konidaris","year":"2011","journal-title":"Proc 25nd AAAI Conf Artif Intell"},{"key":"ref32","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1190"},{"key":"ref37","author":"dhariwal","year":"2017","journal-title":"OpenAI Baselines"},{"key":"ref36","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref35","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"arXiv 1802 09464"},{"key":"ref34","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref10","author":"russell","year":"2009","journal-title":"Artificial Intelligence A Modern Approach"},{"key":"ref40","first-page":"2133","article-title":"Dynamic action repetition for deep reinforcement learning","author":"lakshminarayanan","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref11","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume":"15","author":"ross","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/09540091.2018.1443318"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref15","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref17","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref18","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume":"70","author":"vezhnevets","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30484-3_9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref4","first-page":"2935","article-title":"Playing hard exploration games by watching youtube","author":"aytar","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"2652","article-title":"Expressing arbitrary reward functions as potential-based advice","author":"harutyunyan","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref3","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"griffith","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref7","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref2","first-page":"77","article-title":"Effective transfer via demonstrations in reinforcement learning: A preliminary study","author":"wang","year":"2016","journal-title":"Proc AAAI Spring Symposia"},{"key":"ref9","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016","journal-title":"arXiv 1606 06565"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/817"},{"key":"ref20","first-page":"329","article-title":"Introduction and control of subgoals in reinforcement learning","author":"murata","year":"2007","journal-title":"Proc 25th Conf Int Multi-Conf Artif Intell Appl"},{"key":"ref22","first-page":"1922","article-title":"Landmark based reward shaping in reinforcement learning with hidden states","author":"demir","year":"2019","journal-title":"Proc 18th Int Conf Auto Agents Multiagent Syst"},{"key":"ref21","first-page":"3762","article-title":"Belief reward shaping in reinforcement learning","author":"marom","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell (AAAI)"},{"key":"ref24","first-page":"1409","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","volume":"32","author":"li","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref23","first-page":"3504","article-title":"Potential based reward shaping for hierarchical reinforcement learning","author":"gao","year":"2015","journal-title":"Proc 24th Int Conf Artif Intell"},{"key":"ref26","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","author":"wiewiora","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref25","first-page":"8411","article-title":"Learning from trajectories via subgoal discovery","author":"paul","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09459751.pdf?arnumber=9459751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T15:46:42Z","timestamp":1643212002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9459751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3090364","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}