{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:31:45Z","timestamp":1730266305269,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489747","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T22:25:09Z","timestamp":1539987909000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["AC2: A Policy Gradient Actor with Primary and Secondary Critics"],"prefix":"10.1109","author":[{"given":"Alfonso B.","family":"Labao","sequence":"first","affiliation":[]},{"given":"Prospero C.","family":"Naval","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/07474938.2014.956612"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2307\/1269343"},{"key":"ref12","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref14","article-title":"L-moments","author":"hosking","year":"2009","journal-title":"Wiley StatsRef Statistics Reference Online"},{"key":"ref15","article-title":"Qprop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2016","journal-title":"arXiv preprint arXiv 1611 02247"},{"key":"ref16","first-page":"176","article-title":"Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2017","journal-title":"arXiv preprint arXiv 1710 02298"},{"key":"ref18","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref19","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref4","article-title":"Vizdoom: Drqn with prioritized experience replay, double-q learning, & snapshot ensembling","author":"schulze","year":"2018","journal-title":"arXiv preprint arXiv 1801 01000"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080439"},{"key":"ref7","first-page":"5085","article-title":"Arnold: An autonomous agent to play fps games","author":"chaplot","year":"2017","journal-title":"AAAI"},{"key":"ref2","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"Highdimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 03857"},{"key":"ref9","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2018,7,8]]},"location":"Rio de Janeiro","end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489747.pdf?arnumber=8489747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:57:16Z","timestamp":1598245036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489747","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}