Filters








1,553 Hits in 6.1 sec

Enhancing the Monte Carlo Tree Search Algorithm for Video Game Testing [article]

Sinan Ariyurek, Aysu Betin-Can, Elif Surer
2020 arXiv   pre-print
In this paper, we study the effects of several Monte Carlo Tree Search (MCTS) modifications for video game testing.  ...  In this study, we extend the MCTS agent with several modifications for game testing purposes. Furthermore, we present a novel tree reuse strategy.  ...  Monte Carlo Tree Search Monte Carlo Tree Search (MCTS) [9] is a search algorithm that builds a tree to get the best available action.  ... 
arXiv:2003.07813v1 fatcat:zm3n52lrcfh5xpsrgn7uasqbwq

Population seeding techniques for Rolling Horizon Evolution in General Video Game Playing

Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana
2017 2017 IEEE Congress on Evolutionary Computation (CEC)  
In addition, the paper presents a comparison to a Monte Carlo Tree Search algorithm.  ...  While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Algorithms as an interesting  ...  ACKNOWLEDGMENT This work was funded by the EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI) EP/L015846/1.  ... 
doi:10.1109/cec.2017.7969540 dblp:conf/cec/GainaLL17 fatcat:kidirn4uwjd67fev6v3hvdb6cm

Tackling Sparse Rewards in Real-Time Games with Statistical Forward Planning Methods

Raluca D. Gaina, Simon M. Lucas, Diego Pérez-Liébana
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Thus, modifications are proposed for two algorithms, Monte Carlo Tree Search and Rolling Horizon Evolutionary Algorithms, aiming at improving performance in this type of games while maintaining overall  ...  Some games may present plentiful rewards which the agents can use to guide their search for the best solution, whereas others feature sparse reward landscapes that provide little information to the agents  ...  Acknowledgements This work was funded by the EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI) EP/L015846/1.  ... 
doi:10.1609/aaai.v33i01.33011691 fatcat:4tp333earfayjidsimsiz2zery

AlphaGO – An AI in gaming

2017 International Journal of Recent Trends in Engineering and Research  
Gaming industries are looking for new ways to improve the gaming experience for the consumer.  ...  Today with the gaming industry evolving at very high rate and making a huge place for itself in the market.  ...  Monte Carlo tree search (MCTS) In computer science, Monte Carlo tree search (MCTS) is a heuristic search algorithm for some kinds of decision processes, most notably those employed in game play. • Selection  ... 
doi:10.23883/ijrter.2017.3272.xwdqs fatcat:jie7qz52kbfc3ebyh2szgejauq

Statistical Tree-based Population Seeding for Rolling Horizon EAs in General Video Game Playing [article]

Edgar Galván, Oxana Gorshkova, Peter Mooney, Fred Valdez Ameneyro, Erik Cuevas
2020 arXiv   pre-print
Furthermore, we tackle the former limitation by employing a mechanism that allows us to seed part of the population using Monte Carlo Tree Search, a method that has dominated multiple General Video Game  ...  Another limitation is to use a scalar value (fitness value) to direct evolutionary search instead of accounting for a mechanism that informs us how a particular agent behaves during the rolling horizon  ...  The authors wish to acknowledge the DJEI/DES/SFI/HEA Irish Centre for High-End Computing (ICHEC) for the provision of computational facilities and support.  ... 
arXiv:2008.13253v1 fatcat:c3cqnuvwsvcjvaftzvfgxfl3ia

A Survey of Monte Carlo Tree Search Methods

Cameron B. Browne, Edward Powley, Daniel Whitehouse, Simon M. Lucas, Peter I. Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, Simon Colton
2012 IEEE Transactions on Computational Intelligence and AI in Games  
Monte Carlo Tree Search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling.  ...  We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarise the results from the key game and non-game domains to which  ...  MONTE CARLO TREE SEARCH This section introduces the family of algorithms known as Monte Carlo Tree Search (MCTS).  ... 
doi:10.1109/tciaig.2012.2186810 fatcat:z2o6xdkkjvhf3k6hybw65o5r44

Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing [chapter]

Raluca D. Gaina, Jialin Liu, Simon M. Lucas, Diego Pérez-Liébana
2017 Lecture Notes in Computer Science  
Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research has started looking at Evolutionary Algorithms and their potential at matching Tree Search level  ...  Results show that there is scope for the use of these techniques, which in some configurations outperform Monte Carlo Tree Search, and also suggest that further research in these methods could boost their  ...  Open Loop Monte Carlo Tree Search (OLMCTS) Open Loop Monte Carlo Tree Search (OLMCTS) is an MCTS implementation for the GVGAI framework.  ... 
doi:10.1007/978-3-319-55849-3_28 fatcat:yhoq5tkmjvb7vhj4h4ea2wbv5a

Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing [article]

Raluca D. Gaina and Jialin Liu and Simon M. Lucas and Diego Perez-Liebana
2017 arXiv   pre-print
Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research has started looking at Evolutionary Algorithms and their potential at matching Tree Search level  ...  Results show that there is scope for the use of these techniques, which in some configurations outperform Monte Carlo Tree Search, and also suggest that further research in these methods could boost their  ...  Open Loop Monte Carlo Tree Search (OLMCTS) Open Loop Monte Carlo Tree Search (OLMCTS) is an MCTS implementation for the GVGAI framework.  ... 
arXiv:1704.07075v1 fatcat:sqr4h5l3vrgtzek6owj3mcelk4

The 2016 Two-Player GVGAI Competition

Raluca D. Gaina, Adrien Couetoux, Dennis J. N. J. Soemers, Mark H. M. Winands, Tom Vodopivec, Florian Kirchgesner, Jialin Liu, Simon M. Lucas, Diego Perez-Liebana
2018 IEEE Transactions on Games  
The results validate the competition system in assessing generality, as well as showing Monte Carlo Tree Search continuing to dominate by winning the overall Championship.  ...  This paper showcases the setting and results of the first Two-Player General Video Game AI competition, which ran in 2016 at the IEEE World Congress on Computational Intelligence and the IEEE Conference  ...  ACKNOWLEDGMENTS The authors would like to thank all participants of the competition for their work and submitted controllers.  ... 
doi:10.1109/tciaig.2017.2771241 fatcat:lw6rlge5lfbohkhwjv6xab7ykq

Monte-Carlo Tree Search for the Physical Travelling Salesman Problem [chapter]

Diego Perez, Philipp Rohlfshagen, Simon M. Lucas
2012 Lecture Notes in Computer Science  
In an ongoing effort to better understand the performance of MCTS in open-ended realtime video games, we apply MCTS to the Physical Travelling Salesman Problem (PTSP).  ...  However, visualisations of the search indicate that MCTS is currently seeking solutions in a rather greedy manner, and coercing it to balance short term and long term constraints for the PTSP remains an  ...  results than 1-ply Monte Carlo Search.  ... 
doi:10.1007/978-3-642-29178-4_26 fatcat:2eu4z2l4szbr5h3kbnfoqm4qc4

Enhancements for real-time Monte-Carlo Tree Search in General Video Game Playing

Dennis J. N. J. Soemers, Chiara F. Sironi, Torsten Schuster, Mark H. M. Winands
2016 2016 IEEE Conference on Computational Intelligence and Games (CIG)  
This limits the use of domain-specific heuristics. Monte-Carlo Tree Search (MCTS) is a search technique for game playing that does not rely on domain-specific knowledge.  ...  General Video Game Playing (GVGP) is a field of Artificial Intelligence where agents play a variety of realtime video games that are unknown in advance.  ...  ACKNOWLEDGEMENT This work is partially funded by the Netherlands Organisation for Scientific Research (NWO) in the framework of the project GoGeneral, grant number 612.001.121.  ... 
doi:10.1109/cig.2016.7860448 dblp:conf/cig/SoemersSSW16 fatcat:zvr4kr4p2jbsneuuzi3jaznh4e

Frontmatter

Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, Julian Togelius, Michael Wagner
2013 Dagstuhl Publications  
The chapter first summarises the state of the art in search algorithms for games.  ...  This chapter arises from the discussions of an experienced international group of researchers interested in the potential for creative application of algorithms for searching finite discrete graphs, which  ...  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

A special issue on artificial intelligence in computer games: AICG

Hamido Fujita, I-Chen Wu
2012 Knowledge-Based Systems  
in Monte-Carlo Tree Search (MCTS).  ...  For Single-Player games without the functions, this paper proposes a new MCTS variant, called Single-Player Monte Carlo Tree Search (SP-MCTS), an interesting alternative for one-player games.  ... 
doi:10.1016/j.knosys.2012.05.014 fatcat:sfxd6pc3wre73ltetf6w4kic4y

On Monte Carlo Tree Search and Reinforcement Learning

Tom Vodopivec, Spyridon Samothrakis, Branko Ster
2017 The Journal of Artificial Intelligence Research  
Fuelled by successes in Computer Go, Monte Carlo tree search (MCTS) has achieved widespread adoption within the games community.  ...  We show that a straightforward adaptation of RL semantics within tree search can lead to a wealth of new algorithms, for which the traditional MCTS is only one of the variants.  ...  Acknowledgements The authors wish to thank the anonymous reviewers and associate editor for their help in improving this manuscript -their advice helped clarify and enforce the key message of this study  ... 
doi:10.1613/jair.5507 fatcat:igffnyo5hfbyzigzxpp6t6pebi

Monte Carlo Tree Search: Long-term versus short-term planning

Diego Perez, Philipp Rohlfshagen, Simon M. Lucas
2012 2012 IEEE Conference on Computational Intelligence and Games (CIG)  
In this paper we investigate the use of Monte Carlo Tree Search (MCTS) on the Physical Travelling Salesman Problem (PTSP), a real-time game where the player navigates a ship across a map full of obstacles  ...  We also demonstrate that the physics of the PTSP game impose a challenge regarding the optimal order of cities and propose a solution that obtains better results than following the TSP route of minimum  ...  Monte Carlo Tree Search Monte Carlo Tree Search (MCTS) uses selective sampling to estimate the value of a state: starting from the current state (root), MCTS repeatedly simulates sequences of moves, chosen  ... 
doi:10.1109/cig.2012.6374159 dblp:conf/cig/PerezRL12 fatcat:w7argafjofd3lncrlhpphxfrda
« Previous Showing results 1 — 15 out of 1,553 results