{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:10:02Z","timestamp":1761808202288,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/icip.2018.8451491","type":"proceedings-article","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T13:59:22Z","timestamp":1536328762000},"page":"3778-3782","source":"Crossref","is-referenced-by-count":9,"title":["Deep Reinforcement Learning for Playing 2.5D Fighting Games"],"prefix":"10.1109","author":[{"given":"Yu-Jhe","family":"Li","sequence":"first","affiliation":[]},{"given":"Hsin-Yu","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Yu-Jing","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Po-Wei","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1553","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"chen","year":"2017","journal-title":"AAAI"},{"key":"ref11","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":"david","year":"2016","journal-title":"Nature"},{"key":"ref12","first-page":"464","article-title":"Multi-agent reinforcement learning in sequential social dilemmas","author":"joel","year":"2017","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref14","first-page":"2140","author":"lample","year":"2017","journal-title":"Playing fps games with deep reinforcement learning"},{"journal-title":"Starcraft ii A new challenge for reinforcement learning","year":"2017","author":"vinyals","key":"ref15"},{"year":"1999","key":"ref16"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"year":"2011","author":"lf","key":"ref18"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref19"},{"journal-title":"Q-prop Sample-efficient policy gradient with an off-policy critic","year":"2016","author":"shixiang","key":"ref4"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","article-title":"Deep recurrent q-Iearning for partially observable mdps","volume":"abs 1507 6527","author":"hausknecht","year":"2015","journal-title":"CoRR"},{"key":"ref8","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"tejas","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Deep reinforcement learning from human preferences","year":"2017","author":"christiano","key":"ref7"},{"journal-title":"Massively parallel methods for deep reinforcement learning","year":"2015","author":"nair","key":"ref2"},{"journal-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref1"},{"journal-title":"Training agent for first-person shooter game with actor-critic curriculum learning","year":"2016","author":"wu","key":"ref9"},{"year":"2018","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.4.490"},{"journal-title":"The Arcade Learning Environment An Evaluation Platform for General Agents","year":"2013","author":"marc","key":"ref21"}],"event":{"name":"2018 25th IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2018,10,7]]},"location":"Athens, Greece","end":{"date-parts":[[2018,10,10]]}},"container-title":["2018 25th IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8436606\/8451009\/08451491.pdf?arnumber=8451491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T17:54:34Z","timestamp":1643306074000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8451491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icip.2018.8451491","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}