The 2009 Simulated Car Racing Championship

Loiacono, Daniele; Lanzi, Pier Luca; Togelius, Julian; Onieva, Enrique; Pelta, David A.; Butz, Martin V.; Lonneker, T D; Cardamone, Luigi; Pérez, Diego; Sáez, Yago; Preuß, Mike; Quadflieg, Jan

doi:10.1109/tciaig.2010.2050590

Cited by 82 publications

(43 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The winner is generally the competitor whose software played the game best. Some of the most popular competitions have been based on well known games, such as Ms. Pac-Man [21], [17], Super Mario Bros [13], or lesser known games in a well-defined and popular genre, such as the car racing game TORCS [16]. However, in some competitions the player does not submit a high-performing controller, but rather a controller that plays the game in an as human-like manner as possible [11], or even a level generator that generates as entertaining levels as possible for particular players [22].…”

Section: Game Ai Competitionsmentioning

confidence: 99%

Automated Map Generation for the Physical Traveling Salesman Problem

Pérez

Togelius

Samothrakis

et al. 2014

IEEE Trans. Evol. Computat.

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents a method for generating complex problems that allow multiple non-obvious solutions for the Physical Travelling Salesman Problem (PTSP). PTSP is a single-player game adaptation of the classical Travelling Salesman Problem that makes use of a simple physics model: the player has to visit a number of waypoints as quickly as possible by navigating a ship in real time across an obstaclefilled two-dimensional map. The difficulty of this game depends on the distribution of waypoints and obstacles across the twodimensional plane. Due to the physics of the game, the shortest route is not necessarily the fastest, as the ship's momentum makes it difficult to turn sharply at speed. This paper proposes an evolutionary approach to obtaining maps where the optimal solution is not immediately obvious. In particular, any optimal route for these maps should differ distinctively from (a) the optimal distance-based TSP route and (b) the route that corresponds to always approaching the nearest waypoint first. To achieve this, the evolutionary algorithm CMA-ES is employed, where maps, indirectly represented as vectors of real numbers, are evolved to differentiate maximally between a game-playing agent that follows two or more different routes. The results presented in this paper show that CMA-ES is able to generate maps that fulfil the desired conditions.

show abstract

Section: Game Ai Competitionsmentioning

confidence: 99%

Automated Map Generation for the Physical Traveling Salesman Problem

Pérez

Togelius

Samothrakis

et al. 2014

IEEE Trans. Evol. Computat.

Self Cite

View full text Add to dashboard Cite

show abstract

“…This makes it especially attractive as a "black box" optimisation method. A mature Java implementation has been made freely available by the algorithm's creators 3 , which was used to tune the parameters for PUROFMOVIO.…”

Section: B Parameter Tuningmentioning

confidence: 99%

“…Among many others, some of them have been particularly successful: the Ms. Pacman vs. Ghost competition [1] allowed participants to take part in the popular game of PacMan both as the player and the ghost team, exploring agent coordination in the latter case. The Starcraft competition [2] tackled problems like unit management and partially observable game states, and the popular Car Racing Competitions [3] have, as one of their most important features, the player dealing with other drivers.…”

Section: Introductionmentioning

confidence: 99%

The 2013 Multi-objective Physical Travelling Salesman Problem Competition

Pérez¹,

Powley²,

Whitehouse

et al. 2014

2014 IEEE Congress on Evolutionary Computation (CEC)

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents the game, framework, rules and results of the Multi-objective Physical Travelling Salesman Problem (MO-PTSP) Competition, that was held at the 2013 IEEE Conference on Computational Intelligence in Games (CIG). The MO-PTSP is a real-time game that can be seen as a modification of the Travelling Salesman Problem, where the player controls a ship that must visit a series of waypoints in a maze while minimizing three opposing goals: time spent, fuel consumed and damage taken. The rankings of the competition are computed using multi-objective concepts, a novel approach in the field of game artificial intelligence competitions. The winning entry of the contest is also explained in detail. This controller is based on the Monte Carlo Tree Search algorithm, and employed Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for parameter tuning.

show abstract

“…Some of these competitions are based on arcade-style games such as Ms. Pac-Man [7], Cellz [8], X-pilot [9] and a simple 2D racing game [10]. But there are also competitions based on the firstperson shooter Unreal Tournament [11], [12], the modern racing game TORCS [13] and the real-time strategy game StarCraft [14]. The organization, results and summaries of entries of many of these competitions have been written up as journal articles or conference papers, providing an archival reference point for other researchers wishing to use the benchmarks developed for their own experiments; for other competitions, at least the benchmark software and initial experiments have been published.…”

Section: A Previous Game-based Competitions and Benchmarksmentioning

confidence: 99%

The Mario AI Benchmark and Competitions

Karakovskiy

Togelius

2012

IEEE Trans. Comput. Intell. AI Games

Self Cite

111

View full text Add to dashboard Cite

Abstract-This paper describes the Mario AI benchmark, a game-based benchmark for reinforcement learning algorithms and game AI techniques developed by the authors. The benchmark is based on a public domain clone of Nintendo's classic platform game Super Mario Bros, and completely open source. During the last two years, the benchmark has been used in a number of competitions associated with international conferences, and researchers and students from around the world have contributed diverse solutions to try to beat the benchmark. The paper summarises these contributions, gives an overview of the state-of-art in Mario-playing AIs, and chronicles the development of the benchmark. This paper is intended as the definitive point of reference for those using the benchmark for research or teaching.

show abstract

The 2009 Simulated Car Racing Championship

Cited by 82 publications

References 23 publications

Automated Map Generation for the Physical Traveling Salesman Problem

Automated Map Generation for the Physical Traveling Salesman Problem

The 2013 Multi-objective Physical Travelling Salesman Problem Competition

The Mario AI Benchmark and Competitions

Contact Info

Product

Resources

About