{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T16:06:54Z","timestamp":1775146014263,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"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":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671827","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"1337-1348","source":"Crossref","is-referenced-by-count":5,"title":["InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem"],"prefix":"10.1109","author":[{"given":"Markel Sanz","family":"Ausin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamoon","family":"Azizsoltani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Ju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeo Jin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Chi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref38","first-page":"429","article-title":"Learning from demonstration for shaping through inverse reinforcement learning","author":"suay","year":"2016","journal-title":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2018.08.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2018.7571"},{"key":"ref31","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume":"7","author":"ramachandran","year":"2007","journal-title":"IJCAI"},{"key":"ref30","article-title":"Deep reinforcement learning for sepsis treatment","author":"raghu","year":"2017","journal-title":"Workshop on ML for Health NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref35","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":"ref34","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref28","article-title":"Conducting credit assignment by aligning local representations","author":"ororbia","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000002476"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref1","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref20","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"levine","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"3762","author":"marom","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) the 30th innovative Applications of Artificial Intelligence (IAAI-18) and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18)"},{"key":"ref21","article-title":"Expected eligibility traces","author":"madjiheurem","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence volume 35 Association for the Advancement of Artificial Intelligence (AAAI)"},{"key":"ref24","article-title":"Counterfactual credit assignment in model-free reinforcement learning","author":"mesnard","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1961.287775"},{"key":"ref10","article-title":"Delay-aware model-based reinforcement learning for continuous control","author":"chen","year":"2020"},{"key":"ref11","article-title":"Self-imitation learning in sparse reward settings","author":"chen","year":"2020"},{"key":"ref40","author":"sutton","year":"1985","journal-title":"Temporal credit assignment in reinforcement learning"},{"key":"ref12","author":"chollet","year":"0","journal-title":"Keras"},{"key":"ref13","first-page":"12488","article-title":"Hindsight credit assignment","volume":"32","author":"harutyunyan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","author":"ashley","year":"2018","journal-title":"Hill Stable baselines"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13073-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.565702"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1097\/01.CCM.0000217961.75225.E9"},{"key":"ref19","article-title":"Learning to solve the credit assignment problem","author":"lansdell","year":"2019"},{"key":"ref4","article-title":"Rudder: Return decomposition for delayed rewards","author":"arjona-medina","year":"2018"},{"key":"ref3","first-page":"980","article-title":"Unifying temporal and structural credit assignment problems","volume":"2","author":"agogino","year":"2004","journal-title":"Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3311-16.2017"},{"key":"ref5","article-title":"An information-theoretic perspective on credit assignment in reinforcement learning","author":"arumugam","year":"2021"},{"key":"ref8","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/273"},{"key":"ref49","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref9","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref46","author":"john","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref45","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015"},{"key":"ref48","article-title":"On learning intrinsic rewards for policy gradient methods","author":"zheng","year":"2018"},{"key":"ref47","article-title":"Shaping rewards for reinforcement learning with imperfect demonstrations using generative models","author":"wu","year":"2020"},{"key":"ref42","author":"sutton","year":"1990","journal-title":"Time-Derivative Models of Pavlonian Reinforcement"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref44","first-page":"10376","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","author":"trott","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32 Annual Conference on Neural Information Processing Systems 2019 NeurIPS 2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992697"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09671827.pdf?arnumber=9671827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:55:30Z","timestamp":1652201730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671827","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}