Filters








67 Hits in 3.9 sec

Evolving competitive car controllers for racing games with neuroevolution

Luigi Cardamone, Daniele Loiacono, Pier Luca Lanzi
2009 Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09  
In this paper we apply NeuroEvolution of Augmenting Topologies (NEAT), a well known neuroevolution approach, to evolve competitive non-player characters for a racing game.  ...  In particular, we focused on The Open Car Racing Simulator (TORCS), an open source car racing simulator, already used as a platform for several scientific competitions dedicated to games.  ...  In particular, we applied NeuroEvolution with Augmenting Topology (NEAT) [17] , a well known neuroevolution approach, to evolve a competitive controller for TORCS.  ... 
doi:10.1145/1569901.1570060 dblp:conf/gecco/CardamoneLL09 fatcat:5tcemhhp6rd3nixviz67wiayn4

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

Sebastian Risi, Julian Togelius
2015 arXiv   pre-print
This paper surveys research on applying neuroevolution (NE) to games.  ...  In neuroevolution, artificial neural networks are trained through evolutionary algorithms, taking inspiration from the way biological brains evolved.  ...  This work on evolving car racing controllers spawned a series of competitions on simulated car racing; the first year's competition built on the same simple racing game [98] , which was exchanged for  ... 
arXiv:1410.7326v3 fatcat:yqynswodpnbgzdf52mlisix3hu

Neuroevolution in Games: State of the Art and Open Challenges

Sebastian Risi, Julian Togelius
2017 IEEE Transactions on Computational Intelligence and AI in Games  
This paper surveys research on applying neuroevolution (NE) to games.  ...  In neuroevolution, artificial neural networks are trained through evolutionary algorithms, taking inspiration from the way biological brains evolved.  ...  This work on evolving car racing controllers spawned a series of competitions on simulated car racing; the first year's competition built on the same simple racing game [128] , which was exchanged for  ... 
doi:10.1109/tciaig.2015.2494596 fatcat:uenp54gg2vffdolr5awox2ayx4

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  ...  engines and game dynamics.  ...  [6] , [5] applied neuroevolution to evolve a driving and an overtaking behavior, in a sophisticated 3D car racing simulator (TORCS).  ... 
doi:10.1109/cig.2011.6032011 dblp:conf/cig/CardamoneCLL11 fatcat:vyprpbm6qfbhnbodkyswqmv5wi

Evaluation Of Evolution Strategy, Genetic Algorithm And Their Hybrid On Evolving Simulated Car Racing Controllers

Hidehiko Okada, Jumpei Tokida
2012 Zenodo  
Car Racing competition.  ...  In th our experimental result on the comparison of three evolutionary algorithms – evolution strategy, genetic algorithm, and their hybrid applied to evolving controller agents for the CIG 2007 Simulated  ...  Car Racing competition 7 .  ... 
doi:10.5281/zenodo.1333104 fatcat:kftfi2pyrbdbnhop74iivc6spe

Evolving neural networks

Risto Miikkulainen
2007 Proceedings of the 2007 GECCO conference companion on Genetic and evolutionary computation - GECCO '07  
racing community -Hand-designed cars and drivers -First step towards real traffic 42 Evolving Good Drivers • Evolving to drive fast without crashing (off road, obstacles) • An interesting  ...  40 51 Competitive Coevolution with NEAT • Complexification elaborates instead of alters -Adding more complexity to existing behaviors • Can establish a coevolutionary arms race -Two populations  ... 
doi:10.1145/1274000.1274119 dblp:conf/gecco/Miikkulainen07 fatcat:4zyvbu3dxjb4hjqqicvwwzvjna

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

Karine da Silva Miras de Araújo, Fabrício Olivetti de França
2016 arXiv   pre-print
In this article, we introduce a framework for testing optimization algorithms with artificial agent controllers in electronic games, called EvoMan, which is inspired in the action-platformer game Mega  ...  A way for dealing with this problem is through Neuroevolution, a method which trains Artificial Neural Networks using evolutionary algorithms.  ...  Competitive Coevolution (CC) [12] is a method of applying Evolutionary Algorithms, so that instead of evolving a single population, two populations are mutually evolved through competition.  ... 
arXiv:1604.00644v2 fatcat:5hk6bxacrnfappdsszkejg4foe

Learning to overtake in TORCS using simple reinforcement learning

Daniele Loiacono, Alessandro Prete, Pier Luca Lanzi, Luigi Cardamone
2010 IEEE Congress on Evolutionary Computation  
In this paper, we applied the Behavior Analysis and Training (BAT) methodology to define a behavior-based architecture for the NPCs in The Open Racing Car Simulator (TORCS), a well-known open source racing  ...  In modern racing games programming non-player characters with believable and sophisticated behaviors is getting increasingly challenging.  ...  In particular, they applied neuroevolution to learn controllers both for radio-controlled car models and for a simpler two-dimensional racing simulator.  ... 
doi:10.1109/cec.2010.5586191 dblp:conf/cec/LoiaconoPLC10 fatcat:yreeg7nkdzhsnpxjf4phc6laey

Constructing Game Agents Through Simulated Evolution [chapter]

Jacob Schrum, Risto Miikkulainen
2015 Encyclopedia of Computer Graphics and Games  
Synonyms: Evolutionary computation, evolutionary algorithms, evolutionary machine-learning, neuroevolution, evolutionary agent design.  ...  Definition: Construction of game agents through simulated evolution is the use of algorithms that model the biological of process of evolution to develop the behavior and/or morphology of game agents.  ...  Another option is to evolve a racecar controller in an environment filled with scripted opponent cars.  ... 
doi:10.1007/978-3-319-08234-9_15-1 fatcat:kq4jh5ro2vgz7iimdncf37uode

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  
In this paper, we overview the 2009 Simulated Car Racing Championship-an event comprising three competitions held in association with the 2009 IEEE Congress on Evolutionary Computation (CEC), the 2009  ...  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  ...  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

Controller for TORCS created by imitation

Jorge Munoz, German Gutierrez, Araceli Sanchis
2009 2009 IEEE Symposium on Computational Intelligence and Games  
The first controller is the winner of the WCCI 2008 Simulated Car Racing Competition, and the second one is a hand coded controller that performs a complete lap in all tracks.  ...  This paper is an initial approach to create a controller for the game TORCS by learning how another controller or humans play the game.  ...  The game is TORCS (The Open Racing Car Simulator 1 , see Figure 1 ), an open car racing simulator that is being used in several competitions of AI.  ... 
doi:10.1109/cig.2009.5286464 dblp:conf/cig/MunozGS09 fatcat:z3xvgiq73bgd3ixqfu67xgachu

Neurovisual Control in the Quake II Environment

Matt Parker, Bobby D. Bryant
2012 IEEE Transactions on Computational Intelligence and AI in Games  
Lastly, we replace the hand-coded supervising non-visual controller with an evolved non-visual neural network controller, eliminating the human aspect from the supervision, and it solves a problem for  ...  Creating artificial intelligence that adequately uses visual data allows controllers to use single cameras for input and to interact with computer games by merely reading the screen render.  ...  Kohl et al. used a car racing simulator as well, but used a static 20x14 grayscale retinal input instead of active vision; they evolved a vehicle warning system which can warn a driver whenever there is  ... 
doi:10.1109/tciaig.2012.2184109 fatcat:atvu6emoyvcnrfv7tjzte4kgke

Learning drivers for TORCS through imitation using supervised methods

Luigi Cardamone, Daniele Loiacono, Pier Luca Lanzi
2009 2009 IEEE Symposium on Computational Intelligence and Games  
In this paper, we apply imitation learning to develop drivers for The Open Racing Car Simulator (TORCS).  ...  Our approach can be classified as a direct method in that it applies supervised learning to learn car racing behaviors from the data collected from other drivers.  ...  We considered two representations of the current state of the car: (i) the set of rangefinder inputs usually employed in simulated car racing competitions [11] , [12] and in neuroevolution experiments  ... 
doi:10.1109/cig.2009.5286480 dblp:conf/cig/CardamoneLL09 fatcat:jewvxvdxzrf5plvtsrrujzevjm

Experiments on Neuroevolution and Online Weight Adaptation in Complex Environments [chapter]

Francisco José Gallego-Durán, Rafael Molina-Carmona, Faraón Llorens-Largo
2013 Lecture Notes in Computer Science  
Concretely, HyperNEAT has shown a great potential for evolving large scale neural networks, by discovering geometric regularities, thus being suitable for evolving complex controllers.  ...  This paper shows a new proposal for online weight adaptation in neuroevolved artificial neural networks, and presents the results of several experiments carried out in a race simulation environment.  ...  It is our belief that more work on this approach could offer more interesting results, as there is still much room for new approaches on online learning through weight updating or even creation/destruction  ... 
doi:10.1007/978-3-642-40643-0_14 fatcat:ihye73j6ovgl5mdlzk6lc4lvhi

How to Run a Successful Game-Based AI Competition

Julian Togelius
2016 IEEE Transactions on Computational Intelligence and AI in Games  
This short paper is a self-help paper for competition organisers and aspiring competition organisers.  ...  While many competitions have been organised based on different games, the success of these competitions is highly varied.  ...  This is the case for both the Simulated Car Racing competition and the Mario AI competition. Keep evolving and being relevant.  ... 
doi:10.1109/tciaig.2014.2365470 fatcat:pqn25zdnzvavbgs4lu4z4cjtqi
« Previous Showing results 1 — 15 out of 67 results