23,668 Hits in 5.2 sec

Evolving the optimal racing line in a high-end racing game

Matteo Botta, Vincenzo Gautieri, Daniele Loiacono, Pier Luca Lanzi
2012 2012 IEEE Conference on Computational Intelligence and Games (CIG)  
In this work, we show how evolutionary computation can be successfully applied to solve this task in a high-end racing game.  ...  Finding a racing line that allows to achieve a competitive lap-time is a key problem in real-world car racing as well as in the development of non-player characters for a commercial racing game.  ...  CONCLUSIONS In this paper, we proposed an approach to evolve an optimal racing line to support the development of a modern racing games.  ... 
doi:10.1109/cig.2012.6374145 dblp:conf/cig/BottaGLL12 fatcat:rt7ak2flifcx7cvljg3uzewawu

GP-RARS: evolving controllers for the Robot Auto Racing Simulator

Yehonatan Shichel, Moshe Sipper
2011 Memetic Computing  
We use evolutionary computation techniques to create real-time reactive controllers for a race-car simulation game: RARS (Robot Auto Racing Simulator).  ...  Using genetic programming to evolve driver controllers, we create highly generalized game-playing agents, able to outperform most human-crafted controllers and all machine-designed ones on a variety of  ...  The goal of the game is fairly simple: one or more cars race on a given track. The cars are positioned at the starting line, and simultaneously start moving when the race begins.  ... 
doi:10.1007/s12293-011-0056-9 fatcat:urfynpznovfbbg6at3th6juxxe

Automatic Track Generation for High-End Racing Games Using Evolutionary Computation

Daniele Loiacono, Luigi Cardamone, Pier Luca Lanzi
2011 IEEE Transactions on Computational Intelligence and AI in Games  
We investigate the application of evolutionary computation to the automatic generation of tracks for high-end racing games.  ...  The results we report show that both singleobjective and multi-objective approaches can successfully evolve tracks with a high degree of diversity both in terms of shape and achievable speeds. 10  ...  ACKNOWLEDGEMENTS The authors wish to thank Marco Colombo for his work on the preliminary implementation of the mapping procedure between genotypes and phenotypes.  ... 
doi:10.1109/tciaig.2011.2163692 fatcat:46annlv4vbgqfoxbdwkixg6cc4

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.  ...  An evolvable track representation is devised, and a multiobjective evolutionary algorithm maximises the entertainment value of the track relative to a particular human player.  ...  [9] on evolving active vision, work which was undertaken not to produce a controller which would follow optimal race-lines but to see what sort of vision system would emerge from the evolutionary process  ... 
doi:10.1109/cig.2007.368106 dblp:conf/cig/TogeliusNL07 fatcat:3klaeinkxfa2pfrbgoedbg32mi

Evolving neural networks

Risto Miikkulainen
2007 Proceedings of the 2007 GECCO conference companion on Genetic and evolutionary computation - GECCO '07  
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  ...  neural nets are a good match -Lends itself to many extensions -Powerful in applications • Easy to adapt to applications -Control, robotics, optimization -Artificial life, biology -Gaming: entertainment  ... 
doi:10.1145/1274000.1274119 dblp:conf/gecco/Miikkulainen07 fatcat:4zyvbu3dxjb4hjqqicvwwzvjna

Personalised track design in car racing games

Theodosis Georgiou, Yiannis Demiris
2016 2016 IEEE Conference on Computational Intelligence and Games (CIG)  
The end result is to provide at a next stage a new track that fits to the user needs, which aids both the training of the driver and their engagement in the game.  ...  We investigate how player models can be created in car racing games. Our user model uses a combination of data from unobtrusive sensors, while the user is playing a car racing simulator.  ...  ACKNOWLEDGMENT The authors would like to thank Loizos Shianios for the help provided on designing the track in the specialised software.  ... 
doi:10.1109/cig.2016.7860435 dblp:conf/cig/GeorgiouD16 fatcat:imgtqhonhjb6zcpdcmkwxapyfu

TrackGen: An interactive track generator for TORCS and Speed-Dreams

Luigi Cardamone, Pier Luca Lanzi, Daniele Loiacono
2015 Applied Soft Computing  
TrackGen is an on-line tool for the generation of tracks for two open-source 3D car racing games (TORCS and Speed Dreams).  ...  It integrates interactive evolution with procedural content generation and comprises two components: (i) a web frontend that maintains the database of all the evolved populations and manages the interaction  ...  Marks and Hom [12] were the first to evolve a set of game rules to obtain a balanced board game which could be equally hard to win from either side and rarely ended with a draw.  ... 
doi:10.1016/j.asoc.2014.11.010 fatcat:vgo2saanwjfptiqxo5glbc5yiu

Generating diverse opponents with multiobjective evolution

Alexandros Agapitos, Julian Togelius, Simon M. Lucas, Jurgen Schmidhuber, Andreas Konstantinidis
2008 2008 IEEE Symposium On Computational Intelligence and Games  
For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well.  ...  Experiments are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of GP-based controllers yield pareto fronts of interesting  ...  We do this by defining a number of such objectives for a car controller in a competitive racing game, and perform a number of experiments where we optimize for several of these objectives simultaneously  ... 
doi:10.1109/cig.2008.5035632 dblp:conf/cig/AgapitosTLSK08 fatcat:hd3g4zfswbhxnlmzesjisrluy4

End-to-End Race Driving with Deep Reinforcement Learning [article]

Maximilian Jaritz, Raoul de Charette, Marin Toromanoff, Etienne Perot, Fawzi Nashashibi
2018 arXiv   pre-print
An Asynchronous Actor Critic (A3C) framework is used to learn the car control in a physically and graphically realistic rally game, with the agents evolving simultaneously on tracks with a variety of road  ...  We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding).  ...  For cars, direct perception [5] and end-to-end control [13] were showcased in the TORCS car racing game using Reinforcement Learning (RL).  ... 
arXiv:1807.02371v2 fatcat:igkqqy42ufh3xdjnqtyxcyxwo4

Computational Intelligence in Racing Games [chapter]

Julian Togelius, Simon M. Lucas, Renzo De Nardi
2007 Studies in Computational Intelligence  
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  ...  This chapter surveys the research of us and others into applying evolutionary algorithms and other forms of computational intelligence to various aspects of racing games.  ...  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

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)  
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  ...  Transfer learning might be a promising approach to boost the learning of non-player characters' behaviors by exploiting some existing knowledge available from a different game.  ...  In [9] evolutionary computation is applied to find the optimal racing line between the shortest path and the maximum curvature path of the track.  ... 
doi:10.1109/cig.2011.6032011 dblp:conf/cig/CardamoneCLL11 fatcat:vyprpbm6qfbhnbodkyswqmv5wi

Driving-Bots with a Neuroevolved Brain: Screaming Racers

F. Gallego, Faraon LLorens, Mar Pujol, Ramon Rizo
2006 Inteligencia Artificial  
These driving-bots can then be used as virtual opponents for different racing games, saving time and money in the development of a realistic AI System.  ...  Of the many different types of games, one of the most popular genres is car racing.  ...  Acknowledgments We would like to thank specifically the work done by Hector Linares, who has collaborated in the implementation of the Graphics engine of the Screaming Racers prototype.  ... 
doi:10.4114/ia.v9i28.859 fatcat:26f6vkvc55ekjpkjesdtr4mzmu

Solving the Balance Problem of On-Line Role-Playing Games Using Evolutionary Algorithms

Haoyang Chen, Yasukuni Mori, Ikuo Matsuba
2012 Journal of Software Engineering and Applications  
In on-line role-playing games (RPG), each race holds some attributes and skills. Each skill contains several abilities such as physical damage, hit rate, etc.  ...  on-line RPGs to maintain the game balance.  ...  the score to the individual for fitness. 3) Subcomponent Optimization: Evolve each population separately by using a different evolutionary algorithm, in turn.  ... 
doi:10.4236/jsea.2012.58066 fatcat:sdqubu5yq5bcpmnwccvrzezk6q

Evolutionary spiking neural networks as racing car controllers

Elias Yee, Jason Teo
2011 2011 11th International Conference on Hybrid Intelligent Systems (HIS)  
The Izhikevich spiking neural network model is investigated as a method to develop controllers for a simple, but not trivial, car racing game, called TORCS.  ...  The controllers are evolved using Evolutionary Programming, and the performance of the best individuals is compared with the hand-coded controller included with the Simulated Car Racing Championship API  ...  The fitness of a controller is given by the where d raced is the total distance raced, the car, and T max is the maximum number of game ticks in each race.  ... 
doi:10.1109/his.2011.6122141 dblp:conf/his/YeeT11 fatcat:fewfeallenhj3kdigrlrh7gcua

Robust player imitation using multiobjective evolution

Niels van Hoorn, Julian Togelius, Daan Wierstra, Jurgen Schmidhuber
2009 2009 IEEE Congress on Evolutionary Computation  
This idea is explored in the context of a modern racing game.  ...  It is proposed that better solutions to this problem can be built on multiobjective evolutionary algorithms, with objectives relating both to traditional progress-based fitness (playing the game well)  ...  Not surprisingly, the controllers perform best on the tracks they were evolved on, much in line with the results in [11] .  ... 
doi:10.1109/cec.2009.4983007 dblp:conf/cec/HoornTWS09 fatcat:ifbvsf4hxzaodpuvnb4hitgtmm
« Previous Showing results 1 — 15 out of 23,668 results