{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T22:38:30Z","timestamp":1783377510803,"version":"3.54.6"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/devlrn.2018.8761044","type":"proceedings-article","created":{"date-parts":[[2019,7,16]],"date-time":"2019-07-16T00:17:08Z","timestamp":1563236228000},"page":"175-180","source":"Crossref","is-referenced-by-count":10,"title":["Deep Reinforcement Learning by Parallelizing Reward and Punishment using the MaxPain Architecture"],"prefix":"10.1109","author":[{"given":"Jiexin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Elfwing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiji","family":"Uchibe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615000"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1996.568989"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329799"},{"key":"ref13","article-title":"Extending the openai gym for robotics: a toolkit for reinforcement learning using ros and gazebo","author":"zamora","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref4","first-page":"2750","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume":"30","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"761","article-title":"Horde: A Scalable Real-time Architecture for Learning Knowledge from Unsupervised Sensorimotor Interaction Categories and Subject Descriptors","author":"sutton","year":"2011","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref5","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"van seijen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0053-12.2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1519829113"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"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":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45720-8_43"}],"event":{"name":"2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","location":"Tokyo, Japan","start":{"date-parts":[[2018,9,17]]},"end":{"date-parts":[[2018,9,20]]}},"container-title":["2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/8753819\/8760502\/08761044.pdf?arnumber=8761044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T00:59:10Z","timestamp":1565657950000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/8761044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":13,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/devlrn.2018.8761044","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}