Filters








30,723 Hits in 5.5 sec

Transfer of driving behaviors across different racing games

Luigi Cardamone, Antonio Caiazzo, Daniele Loiacono, Pier Luca Lanzi
2011 2011 IEEE Conference on Computational Intelligence and Games (CIG'11)  
engines and game dynamics.  ...  In this paper, we investigate how to transfer driving behaviors from The Open Racing Car Simulator (TORCS) to VDrift, which are two well known open-source racing games featuring rather different physics  ...  Evolution From Scratch In general, applying neuroevolution to learn a target behavior in a given game is not an easy task.  ... 
doi:10.1109/cig.2011.6032011 dblp:conf/cig/CardamoneCLL11 fatcat:vyprpbm6qfbhnbodkyswqmv5wi

Evolving neural networks

Risto Miikkulainen
2007 Proceedings of the 2007 GECCO conference companion on Genetic and evolutionary computation - GECCO '07  
'07) 57 • "Evolution works by tinkering"-So does neuroevolution -Initial disadvantage turns into novel advantage Video Games • Economically and socially important • Adaptation an important future  ...  agents trained to battle each other -Player trains agents through excercises -Agents evolve in real time -Agents and player collaborate in battle • New genre: Learning is the game • Challenging platform  ... 
doi:10.1145/1274000.1274119 dblp:conf/gecco/Miikkulainen07 fatcat:4zyvbu3dxjb4hjqqicvwwzvjna

The mental arms race amplifier

Michael R. Rose
1980 Human Ecology (New York, N.Y.)  
Therefore, the rapid increase in hominid brain size over the last million years cannot be explained by selection for basic tool use alone. 350o alternative theories, here termed the ecological adaptation  ...  hypothesis and the intraspecific competition hypothesis, are reviewed and rejected.  ...  My hypothesis rests on the assumption that after an initial period of exclusively ecological adaptation, both ecological adaptation and intraspecific competition depended on learned techniques, tool use  ... 
doi:10.1007/bf01561028 fatcat:5uo52kxobjb7tal3ka65cslnka

Neuroevolution in Games: State of the Art and Open Challenges

Sebastian Risi, Julian Togelius
2017 IEEE Transactions on Computational Intelligence and AI in Games  
We analyse the application of NE in games along five different axes, which are the role NE is chosen to play in a game, the different types of neural networks used, the way these networks are evolved,  ...  how the fitness is determined and what type of input the network receives.  ...  Lucas, Peter Stone and Olivier Delalleau.  ... 
doi:10.1109/tciaig.2015.2494596 fatcat:uenp54gg2vffdolr5awox2ayx4

Evolutionary computation and games

S.M. Lucas, G. Kendall
2006 IEEE Computational Intelligence Magazine  
Natural evolution can be considered to be a game in which the rewards for an organism that plays a good game of life are the propagation of its genetic material to its successors and its continued survival  ...  The "Evolving Game Strategies" sidebar discusses the main design decisions involved when applying evolution in this way.  ...  This support was instrumental in establishing the IEEE Symposium on Computational Intelligence and Games conference series.  ... 
doi:10.1109/mci.2006.1597057 fatcat:6o7yidxnirftvarbpx2fcxqh44

Neuroevolution in Games: State of the Art and Open Challenges [article]

Sebastian Risi, Julian Togelius
2015 arXiv   pre-print
We analyse the application of NE in games along five different axes, which are the role NE is chosen to play in a game, the different types of neural networks used, the way these networks are evolved,  ...  how the fitness is determined and what type of input the network receives.  ...  It would probably involve the evolution of indirectly-encoded networks with adaptive weights [67, 68] . E.  ... 
arXiv:1410.7326v3 fatcat:yqynswodpnbgzdf52mlisix3hu

Page 488 of Journal of Physical Education, Recreation & Dance (JOPERD) Vol. 8, Issue 8 [page]

1937 Journal of Physical Education, Recreation & Dance (JOPERD)  
This form of activity involves both a race and a game and can include very few or quite a number of game and sport skills.  ...  Relay Races Pupils in every stage of development seem to derive a great deal of pleasure and satisfaction when participating in a relay.  ... 

Computational Intelligence in Racing Games [chapter]

Julian Togelius, Simon M. Lucas, Renzo De Nardi
2007 Studies in Computational Intelligence  
of racing tracks, comparisons of evolution with other forms of reinforcement learning, and modelling and controlling physical cars.  ...  It is suggested that computational intelligence can be used in different but complementary ways in racing games, and that there is unrealised potential for cross-fertilisation between research in evolutionary  ...  Acknowledgements We thank Owen Holland, Richard Newcombe and Hugo Marques for their valuable input at various stages of the work described here.  ... 
doi:10.1007/978-3-540-72705-7_3 fatcat:3jjfbtehhbd6hatca6fhaa2uaa

Horse Racing With Sheep Ankle Bones: The Play of Nomadic Children in Mongolia

Javzandulam Batsaikhan, Candace Kaye
2017 Journal of Childhood Studies  
encouraging tenacity in daily life.  ...  The article first reviews the cultural concept of play within discussions of adaptation, evolutionary process, and a culture-specific phenomenon, proceeds to examine how Mongolian traditional play encourages  ...  , evolution, and a specific cultural environment.  ... 
doi:10.18357/jcs.v42i3.17893 fatcat:5jsslfsruvbj7pd7kw5fv2jkju

Towards automatic personalised content creation for racing games

Julian Togelius, Renzo De Nardi, Simon M. Lucas
2007 2007 IEEE Symposium on Computational Intelligence and Games  
Evolutionary algorithms are commonly used to create high-performing strategies or agents for computer games. In this paper, we instead choose to evolve the racing tracks in a car racing game.  ...  We believe this approach opens up interesting new research questions and is potentially applicable to commercial racing games.  ...  ACKNOWLEDGEMENTS We are thankful to Owen Holland, Georgios Yannakakis, Richard Newcombe and Hugo Marques for insightful discussions.  ... 
doi:10.1109/cig.2007.368106 dblp:conf/cig/TogeliusNL07 fatcat:3klaeinkxfa2pfrbgoedbg32mi

Online evolution in Unreal Tournament 2004

Matthew Patrick
2010 Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games  
Traditional approaches to game AI often feature behaviour that is scripted and predictable. Previous attempts at adaptive AI have struggled to get agents to learn quickly enough.  ...  This paper aims to show adaptation using online evolution is feasible and that it can can be incorporated with minimal change to the existing AI.  ...  Steve Rabin for his advice regarding the applicability of machine learning to computer games. This paper also relies heavily on the Pogamut system for interfacing Java with Unreal Tournament 2004.  ... 
doi:10.1109/itw.2010.5593348 dblp:conf/cig/Patrick10 fatcat:tvpi6f4op5e6bccaehjy2m36bq

Adversarial Genetic Programming for Cyber Security: A Rising Application Domain Where GP Matters

Una-May O'Reilly, Jamal Toutouh, Marcos Pertierra, Daniel Prado Sanchez, Anthony Erb Luogo, Jonathan Kelly, Erik Hemberg
2020 Zenodo  
We present a framework called RIVALS which supports the study of network security arms races.  ...  Adversarial Genetic Programming for Cyber Security encompasses extant and immediate research efforts in a vital problem domain, arguably occupying a position at the frontier where GP matters.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements.  ... 
doi:10.5281/zenodo.4593284 fatcat:mpwyc4xbhbhahlaagf44a22abe

Adversarial genetic programming for cyber security: a rising application domain where GP matters

Una-May O'Reilly, Jamal Toutouh, Marcos Pertierra, Daniel Prado Sanchez, Dennis Garcia, Anthony Erb Luogo, Jonathan Kelly, Erik Hemberg
2020 Genetic Programming and Evolvable Machines  
We present a framework called RIVALS which supports the study of network security arms races.  ...  Adversarial Genetic Programming for Cyber Security encompasses extant and immediate research efforts in a vital problem domain, arguably occupying a position at the frontier where GP matters.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements.  ... 
doi:10.1007/s10710-020-09389-y fatcat:pptcxqfc6zeptdstzl3ipewrym

The 2009 Simulated Car Racing Championship

Daniele Loiacono, Pier Luca Lanzi, Julian Togelius, Enrique Onieva, David A Pelta, Martin V Butz, Thies D Lönneker, Luigi Cardamone, Diego Perez, Yago Sáez, Mike Preuss, Jan Quadflieg
2010 IEEE Transactions on Computational Intelligence and AI in Games  
ACM Genetic and Evolutionary Computation Conference (GECCO), and the 2009 IEEE Symposium on Computational Intelligence and Games (CIG).  ...  Finally, we summarize the championship results, followed by a discussion about what the organizers learned about 1) the development of high-performing car racing controllers and 2) the organization of  ...  Lanzi, and J. Togelius, would like to thank all the competitors, without whom there would be no competition or championship at all.  ... 
doi:10.1109/tciaig.2010.2050590 fatcat:uqxuu55u6zgy7ne5cabbhrjeiy

An electronic-game framework for evaluating coevolutionary algorithms [article]

Karine da Silva Miras de Araújo, Fabrício Olivetti de França
2016 arXiv   pre-print
The environment can be configured to run in different experiment modes, as single evolution, coevolution and others.  ...  One of the common artificial intelligence applications in electronic games consists of making an artificial agent learn how to execute some determined task successfully in a game environment.  ...  In this work it was verified that the coevolved controllers achieved a better generalization for the game challenges than the standard evolution.  ... 
arXiv:1604.00644v2 fatcat:5hk6bxacrnfappdsszkejg4foe
« Previous Showing results 1 — 15 out of 30,723 results