{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:07:09Z","timestamp":1730207229247,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/cig.2018.8490427","type":"proceedings-article","created":{"date-parts":[[2018,10,16]],"date-time":"2018-10-16T03:37:41Z","timestamp":1539661061000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Tabular Reinforcement Learning in Real-Time Strategy Games via Options"],"prefix":"10.1109","author":[{"given":"Anderson R.","family":"Tavares","sequence":"first","affiliation":[]},{"given":"Luiz","family":"Chaimowicz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","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"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2009.5286483"},{"key":"ref30","first-page":"103","article-title":"Safe strategies for agent modelling in games","author":"mccracken","year":"2004","journal-title":"AAAI Fall Symposium on Artificial Multi-Agent Learning"},{"key":"ref34","article-title":"Speeding up Tabular Reinforcement Learning Using State-Action Similarities","author":"rosenfeld","year":"0","journal-title":"Adaptive Learning Agents Workshop at AAMAS"},{"key":"ref10","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2012.6374183"},{"key":"ref12","article-title":"Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks","author":"usunier","year":"2016","journal-title":"Tech Rep"},{"key":"ref13","article-title":"Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games","author":"peng","year":"2017","journal-title":"Tech Rep"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref15","article-title":"The combinatorial multi-armed bandit problem and its application to real-time strategy games","author":"ontan\u00f3n","year":"2013","journal-title":"AAAI Conference on Artificial Intelligence in Interactive Digital Entertainment (AIIDE)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633627"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/11536406_4","article-title":"Learning to win: Case-based plan selection in a real-time strategy game","author":"aha","year":"2005","journal-title":"Case-Based Reasoning Research and Development"},{"key":"ref19","first-page":"93","article-title":"Rock, Paper, StarCraft: Strategy Selection in Real-Time Strategy Games","author":"tavares","year":"2016","journal-title":"AAAI Conference on Artificial Intelligence in Interactive Digital Entertainment (AIIDE)"},{"key":"ref28","article-title":"Fast Heuristic Search for RTS Game Combat Scenarios","author":"churchill","year":"2012","journal-title":"AAAI Conference on Artificial Intelligence in Interactive Digital Entertainment (AIIDE)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/522"},{"key":"ref27","first-page":"531","article-title":"Towards a Unified Theory of State Abstraction for MDPs","author":"li","year":"2006","journal-title":"Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633643"},{"key":"ref6","article-title":"Puppet Search: Enhancing Scripted Behavior by Look-Ahead Search with Applications to Real-Time Strategy Games","author":"barriga","year":"2015","journal-title":"AAAI Conference on Artificial Intelligence in Interactive Digital Entertainment (AIIDE)"},{"article-title":"Algorithms or actions?: A study in large-scale reinforcement learning","year":"0","author":"tavares","key":"ref29"},{"key":"ref5","first-page":"114","article-title":"Portfolio Online Evolution in StarCraft","author":"wang","year":"2016","journal-title":"AAAI Conference on Artificial Intelligence in Interactive Digital Entertainment (AIIDE)"},{"key":"ref8","article-title":"Game Tree Search Based on Non-Deterministic Action Scripts in Real-Time Strategy Games","author":"barriga","year":"0","journal-title":"IEEE Transactions on Computational Intelligence and AI in Games"},{"key":"ref7","first-page":"1652","article-title":"Adversarial Hierarchical-Task Network Planning for Complex Real-Time Games","author":"onta\u00f1\u00f3n","year":"2015","journal-title":"International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref2","first-page":"100","article-title":"Improving Monte Carlo Tree Search Policies in StarCraft via Probabilistic Models Learned from Replay Data","author":"uriarte","year":"2016","journal-title":"AAAI Conference on Artificial Intelligence in Interactive Digital Entertainment (AIIDE)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080430"},{"key":"ref1","first-page":"66","article-title":"Hierarchical Adversarial Search Applied to Real-Time Strategy Games","author":"stanescu","year":"2014","journal-title":"AAAI Conference on Artificial Intelligence in Interactive Digital Entertainment (AIIDE)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2007.368082"},{"key":"ref22","article-title":"The arcade learning environment: An evaluation platform for general agents","author":"bellemare","year":"2012","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2286295"},{"key":"ref24","first-page":"3675","article-title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","author":"kulkarni","year":"2016","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref23","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":"ref26","first-page":"157","article-title":"Markov games as a framework for multi-agent rein forcement learning","author":"littman","year":"1994","journal-title":"International Conference on Machine Learning (ICML) New Brunswick NJ"},{"key":"ref25","first-page":"2295","article-title":"A Laplacian Framework for Option Discovery in Reinforcement Learning","author":"machado","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"}],"event":{"name":"2018 IEEE Conference on Computational Intelligence and Games (CIG)","start":{"date-parts":[[2018,8,14]]},"location":"Maastricht","end":{"date-parts":[[2018,8,17]]}},"container-title":["2018 IEEE Conference on Computational Intelligence and Games (CIG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8473398\/8490359\/08490427.pdf?arnumber=8490427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T20:32:47Z","timestamp":1643229167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8490427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/cig.2018.8490427","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}