Improving RTS Game AI by Supervised Policy Learning, Tactical Search, and Deep Reinforcement Learning
作者： Nicolas A. Barriga , Marius Stanescu , Felipe Besoain , Michael Buro
关键词:
摘要: … Learning State Evaluation and Strategy Selection in μRTS In this section, … machine learning techniques can be used to estimate state values and learning whole-game playing strategies…
sci-hub.se 参考文章(39)
Raph Koster, Will Wright, A Theory of Fun for Game Design ,(2004)
Alexander Kovarsky, Michael Buro, Heuristic search applied to abstract combat games Lecture Notes in Computer Science. pp. 66- 78 ,(2005) , 10.1007/11424918_9
Ming Tan, Multi-agent reinforcement learning: independent vs. cooperative agents international conference on machine learning. pp. 487- 494 ,(1997) , 10.1016/B978-1-55860-307-3.50049-6
Abdallah Saffidine, Michael Buro, David Churchill, Fast heuristic search for RTS game combat scenarios national conference on artificial intelligence. pp. 112- 117 ,(2012)
Volodymyr Mnih, Ioannis Antonoglou, Koray Kavukcuoglu, Daan Wierstra, Martin A. Riedmiller, Alex Graves, David Silver, Playing Atari with Deep Reinforcement Learning arXiv: Learning. ,(2013)
Michael Buro, Graham Erickson, Global state evaluation in StarCraft national conference on artificial intelligence. pp. 112- 118 ,(2014)
Michael Buro, Marius Stanescu, Sergio Poo Hernandez, Graham Erickson, Russel Greiner, Predicting army combat outcomes in StarCraft national conference on artificial intelligence. pp. 86- 92 ,(2013)
David Churchill, Michael Buro, Portfolio greedy search and simulation for large-scale combat in starcraft computational intelligence and games. pp. 1- 8 ,(2013) , 10.1109/CIG.2013.6633643
Adam Eck, Leen-Kiat Soh, Sam Devlin, Daniel Kudenko, Potential-based reward shaping for finite horizon online POMDP planning Autonomous Agents and Multi-Agent Systems. ,vol. 30, pp. 403- 445 ,(2016) , 10.1007/S10458-015-9292-6
A.G. Barto, R.S. Sutton, Reinforcement Learning: An Introduction ,(1988)