{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T09:49:27Z","timestamp":1770284967219,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650872","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Reward-Punishment Reinforcement Learning with Maximum Entropy"],"prefix":"10.1109","author":[{"given":"Jiexin","family":"Wang","sequence":"first","affiliation":[{"name":"ATR Computational Neuroscience Laboratories,Dept. Brain Robot Interface,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eiji","family":"Uchibe","sequence":"additional","affiliation":[{"name":"ATR Computational Neuroscience Laboratories,Dept. Brain Robot Interface,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329799"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0400-07.2007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0053-12.2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1519829113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2018.8761044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.12.001"},{"key":"ref7","article-title":"An alternative softmax operator for reinforcement learning","volume-title":"Proc. of the 34th International Conference on Machine Learning","author":"Asadi"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992700"},{"key":"ref10","article-title":"Learning to solve multiple goals","volume-title":"PhD thesis","author":"Karlsson","year":"1997"},{"key":"ref11","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"van Seijen","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3118.003.0018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45720-8_43"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615000"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2019.8850699"},{"key":"ref17","first-page":"744","article-title":"A story of two streams: Reinforcement learning models from human behavior and neuropsychiatry","volume-title":"Proc. of the 19th International Conference on Autonomous Agents and Multi-Agent Systems","author":"Lin"},{"key":"ref18","article-title":"Taming the noise in reinforcement learning via soft updates","volume-title":"Proc. of the 32nd Conference on Uncertainty in Artificial Intelligence","author":"Fox"},{"key":"ref19","first-page":"3207","article-title":"Dynamic policy programming","volume":"13","author":"Azar","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553508"},{"key":"ref21","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. of the 34th International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. of the 35th International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref23","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"Sergey","year":"2018"},{"key":"ref24","first-page":"2695","article-title":"Theoretical analysis of efficiency and robustness of softmax and gap-increasing operators in reinforcement learning","volume-title":"Proc. of the 22nd International Conference on Artificial Intelligence and Statistics","author":"Kozuno"},{"key":"ref25","article-title":"Maximum entropy rl (provably) solves some robust rl problems","volume-title":"Proc. of the 10th International Conference on Learning and Representations","author":"Eysenbach"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650872.pdf?arnumber=10650872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:09:39Z","timestamp":1725948579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650872","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}