{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T15:06:48Z","timestamp":1730214408035,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/devlrn.2019.8850699","type":"proceedings-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T03:40:48Z","timestamp":1569901248000},"page":"37-42","source":"Crossref","is-referenced-by-count":3,"title":["Reward-Punishment Actor-Critic Algorithm Applying to Robotic Non-grasping Manipulation"],"prefix":"10.1109","author":[{"given":"Taisuke","family":"Kobayashi","sequence":"first","affiliation":[]},{"given":"Takumi","family":"Aotani","sequence":"additional","affiliation":[]},{"given":"Julio Rogelio","family":"Guadarrama-Olvera","sequence":"additional","affiliation":[]},{"given":"Emmanuel","family":"Dean-Leon","sequence":"additional","affiliation":[]},{"given":"Gordon","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45720-8_43"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2224370"},{"key":"ref13","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1901\/jeab.1972.17-15"},{"key":"ref16","first-page":"1","article-title":"True online temporal-difference learning","volume":"17","author":"van seijen","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00442"},{"key":"ref19","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"},{"journal-title":"Emer-gence of locomotion behaviours in rich environments","year":"2017","author":"heess","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329799"},{"key":"ref5","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2014.952493"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2412554"},{"journal-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"schulman","key":"ref9"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01510-8"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1126\/science.1091277","article-title":"Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication","volume":"304","author":"jaeger","year":"2004","journal-title":"Science"}],"event":{"name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","start":{"date-parts":[[2019,8,19]]},"location":"Oslo, Norway","end":{"date-parts":[[2019,8,22]]}},"container-title":["2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8843356\/8850675\/08850699.pdf?arnumber=8850699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:49:39Z","timestamp":1658094579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8850699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2019.8850699","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}