{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T11:26:30Z","timestamp":1725708390723},"reference-count":16,"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\/cig.2019.8847999","type":"proceedings-article","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T01:49:14Z","timestamp":1569548954000},"page":"1-4","source":"Crossref","is-referenced-by-count":2,"title":["Modified PPO-RND Method for Solving Sparse Reward Problem in ViZDoom"],"prefix":"10.1109","author":[{"given":"Jia-Chi","family":"Chen","sequence":"first","affiliation":[]},{"given":"Tao-Hsing","family":"Chang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"29","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"2015","journal-title":"AAAI Fall Symposium Series"},{"key":"ref11","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"Journal of Machine Learning Resaerch"},{"article-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"schulman","key":"ref12"},{"article-title":"Intrinsic motivation and atuomatic curricula via asymmetric selfplay","year":"2018","author":"sukhbaatar","key":"ref13"},{"key":"ref14","article-title":"Empowerment: A universal agentcentric measure of control","author":"klyubin","year":"2005","journal-title":"IEEE Congress on Evolutionary Computation"},{"key":"ref15","article-title":"Exploration: A study of countbased exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref16","article-title":"Unifying Count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref4","first-page":"1","article-title":"ViZDoom: A Doom-based AI research platform for visual reinforcement learning","author":"kempka","year":"2017","journal-title":"IEEE Conference on Computational Intelligence and Games (CIG)"},{"article-title":"Exploration by Random Network Distillation","year":"2018","author":"burda","key":"ref3"},{"key":"ref6","article-title":"ViZDoom Competitions: Playing Doom from Pixels","author":"wydmuch","year":"2018","journal-title":"IEEE Transactions on Games"},{"article-title":"Episodic curiosity through reachability","year":"2018","author":"savinov","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490448"},{"key":"ref7","first-page":"1","article-title":"ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning, & Snapshot Ensembling","author":"schulze","year":"2018","journal-title":"Proceedings of SAI Intelligent Systems Conference"},{"key":"ref2","first-page":"230","article-title":"Formal theory of creativity, fun, and intrinsic motivation","author":"schmidhuber","year":"1990","journal-title":"IEEE Transactions on Autonomous Mental Development"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref9","first-page":"2140","article-title":"Playing FPS games with deep reinforcement learning","author":"lample","year":"2016","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"}],"event":{"name":"2019 IEEE Conference on Games (CoG)","start":{"date-parts":[[2019,8,20]]},"location":"London, United Kingdom","end":{"date-parts":[[2019,8,23]]}},"container-title":["2019 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8844551\/8847948\/08847999.pdf?arnumber=8847999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:47:05Z","timestamp":1658155625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8847999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8847999","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}