Filters








10,219 Hits in 5.8 sec

Multi-Agent Actor-Critic with Hierarchical Graph Attention Network

Heechang Ryu, Hayong Shin, Jinkyoo Park
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This prevents such policies from being applied to more complex multi-agent tasks.  ...  The hierarchical graph attention network is specially designed to model the hierarchical relationships among multiple agents that either cooperate or compete with each other to derive more advanced strategic  ...  vs. Predator-Prey The next game we consider is 3 vs. 3 predator-prey game, a variant of the original 3 vs. 1 predator-prey game. The game rules are identical to those of 3 vs. 1 predator-prey game.  ... 
doi:10.1609/aaai.v34i05.6214 fatcat:pydb25njo5a2vliumgqrzwgfh4

StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning [article]

Kun Shao, Yuanheng Zhu, Dongbin Zhao
2018 arXiv   pre-print
In small scale scenarios, our units successfully learn to combat and defeat the built-in AI with 100 curriculum transfer learning method is used to progressively train a group of units, and shows superior  ...  Real-time strategy games have been an important field of game artificial intelligence in recent years.  ...  ACKNOWLEDGMENT We would like to thank Qichao Zhang, Yaran Chen, Dong Li, Zhentao Tang and Nannan Li for the helpful comments and discussions about this work and paper writing.  ... 
arXiv:1804.00810v1 fatcat:mlskaiafdjd4rdfdtvwq7wozaa

Dungeon Crawl Stone Soup as an Evaluation Domain for Artificial Intelligence [article]

Dustin Dannenhauer, Michael W. Floyd, Jonathan Decker, David W. Aha
2019 arXiv   pre-print
We also highlight an ongoing effort to build an API for AI researchers in the spirit of recent game APIs such as MALMO, ELF, and the Starcraft II API.  ...  This paper describes the properties of Dungeon Crawl Stone Soup that are conducive to evaluating new approaches of AI systems.  ...  We also described an ongoing effort to build an API for AI agents to play and be evaluated in this game.  ... 
arXiv:1902.01769v1 fatcat:dqlpvrxkqvcotef4ju45shyw7q

Multi-Agent Actor-Critic with Hierarchical Graph Attention Network [article]

Heechang Ryu, Hayong Shin, Jinkyoo Park
2019 arXiv   pre-print
This prevents such policies from being applied to more complex multi-agent tasks.  ...  The hierarchical graph attention network is specially designed to model the hierarchical relationships among multiple agents that either cooperate or compete with each other to derive more advanced strategic  ...  vs. Predator-Prey The next game we consider is 3 vs. 3 predator-prey game, a variant of the original 3 vs. 1 predator-prey game. The game rules are identical to those of 3 vs. 1 predator-prey game.  ... 
arXiv:1909.12557v2 fatcat:3logs5g25begbiq3shexosgype

Frontmatter

Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, Julian Togelius, Michael Wagner
2013 Dagstuhl Publications  
Finally the chapter looks forward to promising techniques which might bring some of the success achieved in games such as Go and Chess, to real-time video games.  ...  have been highly successful in a wide range of application areas, to address a broad range of problems arising in video games.  ...  We expect to see many advances in search-based video game AI in the next few years.  ... 
doi:10.4230/dfu.vol6.12191.i dblp:conf/dagstuhl/X13b fatcat:i4isdb5w4fastcbnczbtsdulkm

If multi-agent learning is the answer, what is the question?

Yoav Shoham, Rob Powers, Trond Grenager
2007 Artificial Intelligence  
We thank them all collectively, with special thanks to members of the multi-agent group at Stanford in the past three years.  ...  The area of learning in multi-agent systems is today one of the most fertile grounds for interaction between game theory and artificial intelligence.  ...  On some special characteristics of multi-agent learning Before launching into specifics, we wish to highlight the special nature of MAL.  ... 
doi:10.1016/j.artint.2006.02.006 fatcat:2iwe7b4xfbhdnm4pi7iy5ph3gm

Learning to recommend game contents for real-time strategy gamers

Hyun-Tae Kim, Kyung-Joong Kim
2014 2014 IEEE Conference on Computational Intelligence and Games  
In this paper, we attempt to propose to use machine learning based on game contents with user's explicit preference (like or dislike).  ...  It is not surprising that there are currently many game videos, increasingly prevalent on the web, to watch professional player's matches.  ...  This is a special property of the game replay analysis. Each game is stored in the binary format of the StarCraft game replay.  ... 
doi:10.1109/cig.2014.6932883 dblp:conf/cig/KimK14 fatcat:kqvjo3fuvzflran7l5exfm2siq

ACognitive Approach to Game Usability and Design: Mental Model Development in Novice Real-Time Strategy Gamers

John Graham, Liya Zheng, Cleotilde Gonzalez
2006 CyberPsychology & Behavior  
This research presents an opportunity for the design of games that are guided by shifts in a player's mental model as opposed to the typical progression through successive performance levels.  ...  In the case of RTS games, the operator is the player and the target system is expressed by the relationships within the game.  ...  ACKNOWLEDGMENTS Special thanks to Bill Brislin (RVMECH) for extensive scenario development and expert consultation on Command & Conquer Generals.  ... 
doi:10.1089/cpb.2006.9.361 pmid:16780404 fatcat:c6upmxfjo5ghfe53ox4ezqvvwu

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI

Sebastian Risi, Mike Preuss
2020 Künstliche Intelligenz  
Therefore, we put a focus on important recent developments, including that advances in Game AI are starting to be extended to areas outside of games, such as robotics or the synthesis of chemicals.  ...  the future of Game AI.  ...  Acknowledgements We would like to thank Mads Lassen, Rasmus Berg Palm, Niels Justesen, Georgios Yannakakis, Marwin Segler, and Christian Igel for comments on earlier drafts of this manuscript.  ... 
doi:10.1007/s13218-020-00647-w fatcat:5apytyqvmbbm7a4fgqmtg423ui

Multi-agent Reinforcement Learning in Bayesian Stackelberg Markov Games for Adaptive Moving Target Defense [article]

Sailik Sengupta, Subbarao Kambhampati
2020 arXiv   pre-print
We show that our learning approach converges to an SSE of a BSMG and then highlight that the learned movement policy (1) improves the state-of-the-art in MTD for web-application security and (2) converges  ...  We situate BSMGs in the landscape of incomplete-information Markov games and characterize the notion of Strong Stackelberg Equilibrium (SSE) in them.  ...  Acknowlegements The research is supported in part by ONR grants N00014-16-1-2892, N00014-18-1-2442, N00014-18-1-2840, N00014-19-1-2119, AFOSR grant FA9550-18-1-0067, DARPA SAIL-ON grant W911NF-19-2-0006  ... 
arXiv:2007.10457v1 fatcat:ddz3g2cezza57lhf3tdhtdkwxa

Non-Linear Monte-Carlo Search in Civilization II

S. R. K. Branavan, David Silver, Regina Barzilay
2011 International Joint Conference on Artificial Intelligence  
Our non-linear Monte-Carlo search wins over 78% of games against the built-in AI of Civilization II. 1  ...  A further significant advantage of this approach is its ability to automatically extract and leverage domain knowledge from external sources such as game manuals.  ...  Any opinions, findings, conclusions, or recommendations expressed in this paper are those of the authors, and do not necessarily reflect the views of the funding organizations.  ... 
doi:10.5591/978-1-57735-516-8/ijcai11-401 dblp:conf/ijcai/BranavanSB11 fatcat:tsn2ejf4zzdbjdlzp4wn536ely

Coordination in multiagent reinforcement learning

Georgios Chalkiadakis, Craig Boutilier
2003 Proceedings of the second international joint conference on Autonomous agents and multiagent systems - AAMAS '03  
A repeated game is made up from repetitions of a single strategic (normal form/ matrix) game… Exploration vs.  ...  [Chalkiadakis & Boutilier] Coordination in MARL: A Bayesian Approach  ... 
doi:10.1145/860575.860689 dblp:conf/atal/ChalkiadakisB03 fatcat:z25xhv4gorhi5hrti7ig5oysxq

Coordination in multiagent reinforcement learning

Georgios Chalkiadakis, Craig Boutilier
2003 Proceedings of the second international joint conference on Autonomous agents and multiagent systems - AAMAS '03  
A repeated game is made up from repetitions of a single strategic (normal form/ matrix) game… Exploration vs.  ...  [Chalkiadakis & Boutilier] Coordination in MARL: A Bayesian Approach  ... 
doi:10.1145/860685.860689 fatcat:odbwvlwvfje6xbyek6xaabikya

Game Plan: What AI can do for Football, and What Football can do for AI

Karl Tuyls, Shayegan Omidshafiei, Paul Muller, Zhe Wang, Jerome Connor, Daniel Hennes, Ian Graham, William Spearman, Tim Waskett, Dafydd Steel, Pauline Luc, Adria Recasens (+24 others)
2021 The Journal of Artificial Intelligence Research  
More recently, AI techniques have been applied to football, due to a huge increase in data collection by professional teams, increased computational power, and advances in machine learning, with the goal  ...  teams, spectators, and broadcasters in the years to come.  ...  Football offers the opportunity for AI to evaluate multi-modal models on synthesized vision, audio, and text data in a unified (though simpler) domain than the broader real world.  ... 
doi:10.1613/jair.1.12505 fatcat:klaw7alkzrhp7kd7ebdefpxh7e

Neuroevolution Based Multi-Agent System with Ontology Based Template Creation for Micromanagement in Real-Time Strategy Games

I. Gabriel, V. Negru, D. Zaharie
2014 Information Technology and Control  
As a baseline we compared the in game AI as well as several other AI solutions that use adaptive mechanisms.  ...  This paper presents a multi-agent system that handles unit micromanagement using online machine learning in real time strategy games.  ...  The first is a full AI vs AI competition where the systems play the game from the beginning until one of them loses.  ... 
doi:10.5755/j01.itc.43.1.4600 fatcat:o4jpgyx5zfdq5dla2rj2zekn7e
« Previous Showing results 1 — 15 out of 10,219 results