Fernando Palero Molina

In order to achieve flow and increase player retention, it is important that games difficulty matches player skills. Being able to evaluate how people play a game is a crucial component for detecting gamers strategies in video-games. One of themain problems in player strategy detection is whether attributes selected to define strategies correctly detect the actions of the player. In this paper, we will study a Real Time Strategy (RTS) game. In RTS the participants make use of units and… Mostrar más

In order to achieve flow and increase player retention, it is important that games difficulty matches player skills. Being able to evaluate how people play a game is a crucial component for detecting gamers strategies in video-games. One of themain problems in player strategy detection is whether attributes selected to define strategies correctly detect the actions of the player. In this paper, we will study a Real Time Strategy (RTS) game. In RTS the participants make use of units and structures to secure areas of a map and/or destroy the opponents resources. We will extract real-time information about the players strategies at several gameplays through a Web Platform. After gathering enough information, the model will be evaluated in terms of unsupervised learning (concretely, K-Means). Finally, we will study the similitude between several gameplays where players use different strategies. Mostrar menos

In the last years, the Video Game industry has growth considerably, capturing the attention of the research community. One of the research hot topics in videogames is related to the identification of gamers behaviour while they are playing the game. This work presents an initial case related to the identification of users behaviour in a particular kind of videogame through gamer interaction extraction and analysis. The Video Game selected in this work is a Tower Defence Game, called OTD, where… Mostrar más

In the last years, the Video Game industry has growth considerably, capturing the attention of the research community. One of the research hot topics in videogames is related to the identification of gamers behaviour while they are playing the game. This work presents an initial case related to the identification of users behaviour in a particular kind of videogame through gamer interaction extraction and analysis. The Video Game selected in this work is a Tower Defence Game, called OTD, where the user needs to build towers, in a 2-D grid, to avoid the enemies to reach the exit point of the level. It has been created a framework that allows extract the information from the game and later use statistical techniques to analyse the gamers behaviour. Finally, some experiments have been carried out to test this framework. Mostrar menos

Para conseguir captar el interés de los jugadores is importante que los
vídeo juegos adapten su dificultad en función de las habilidades del jugador. Ser
capaz de evaluar como juegan los usuarios es un componente crucial para modelar
el comportamiento de los jugadores en los juegos. Uno de los problemas de crear
un modelo de comportamiento de usuario es comprobar si las variable predictoras
detectan correctamente las acciones del jugador. En este artículo, estudiaremos
el… Mostrar más

Para conseguir captar el interés de los jugadores is importante que los
vídeo juegos adapten su dificultad en función de las habilidades del jugador. Ser
capaz de evaluar como juegan los usuarios es un componente crucial para modelar
el comportamiento de los jugadores en los juegos. Uno de los problemas de crear
un modelo de comportamiento de usuario es comprobar si las variable predictoras
detectan correctamente las acciones del jugador. En este artículo, estudiaremos
el juego de código abierto Tower Defense (Open-source Tower Defence OTD),
basado en un tablero 2D en el que aparecen conjunto de hordas enemigas que
deben ser destruidas para evitar que alcancen la salida. Utilizando dicho juego extraeremos
en tiempo real la información de las interacciones usuario y los eventos
del juego utilizando la técnica de ventana deslizante. Una vez obtenida suficiente
información, el modelo se evaluará mediante técnicas de clustering (concretamente,
K-Means y Spectral Cluster). Finalmente, estudiaremos la similitud entre
las diferentes partidas donde los jugadores han utilizado diferentes estrategias. Mostrar menos

Computational intelligence (CI), such as evolutionary computation or swarm intelligence methods, is a set of bio-inspired algorithms that have been widely used to solve problems in areas like planning, scheduling or constraint satisfaction problems. Constrained satisfaction problems (CSP) have taken an important attention from the research community due to their applicability to real problems. Any CSP problem is usually modelled as a constrained graph where the edges represent a set of… Mostrar más

Computational intelligence (CI), such as evolutionary computation or swarm intelligence methods, is a set of bio-inspired algorithms that have been widely used to solve problems in areas like planning, scheduling or constraint satisfaction problems. Constrained satisfaction problems (CSP) have taken an important attention from the research community due to their applicability to real problems. Any CSP problem is usually modelled as a constrained graph where the edges represent a set of restrictions that must be verified by the variables (represented as nodes in the graph) which will define the solution of the problem. This paper studies the performance of two particular CI algorithms, ant colony optimization (ACO) and genetic algorithms (GA), when dealing with graph-constrained models in video games problems. As an application domain, the "Lemmings" video game has been selected, where a set of lemmings must reach the exit point of each level. In order to do that, each level is represented as a graph where the edges store the allowed movements inside the world. The goal of the algorithms is to assign the best skills in each position on a particular level, to guide the lemmings to reach the exit. The paper describes how the ACO and GA algorithms have been modelled and applied to the selected video game. Finally, a complete experimental comparison between both algorithms, based on the number of solutions found and the levels solved, is analysed to study the behaviour of those algorithms in the proposed domain. Mostrar menos

Ant Colony Optimization (ACO) has been successfully applied to a wide number of complex and real domains. From classical optimization problems to video games, these kind of swarm-based approaches have been adapted, to be later used, to search for new meta-heuristic based solutions. This paper presents a simple ACO algorithm that uses a specifically designed heuristic, called common-sense, which has been applied in the classical video game Lemmings. In this game a set of lemmings must reach the… Mostrar más

Ant Colony Optimization (ACO) has been successfully applied to a wide number of complex and real domains. From classical optimization problems to video games, these kind of swarm-based approaches have been adapted, to be later used, to search for new meta-heuristic based solutions. This paper presents a simple ACO algorithm that uses a specifically designed heuristic, called common-sense, which has been applied in the classical video game Lemmings. In this game a set of lemmings must reach the exit point of each level, using a subset of finite number of skills, taking into account the contextual information given from the level. The paper describes both the graph model and the context-based heuristic, designed to implement our ACO approach. Afterwards, two different kind of simulations have been carried out to analyse the behaviour of the ACO algorithm. On the one hand, a micro simulation, where each ant is used to model a lemming, and a macro simulation where a swarm of lemmings is represented using only one ant. Using both kind of simulations, a complete experimental comparison based on the number and quality of solutions found and the levels solved, is carried out to study the behaviour of the algorithm under different game configurations. Mostrar menos

In order to achieve the game flow and increase player retention, it is important that games
difficulty matches player skills. As a consequence, to evaluate how people play a game
is a crucial component, because detecting gamers strategies in video-games, it is possible
to fix the game difficulty. The main problem to detect the strategies is whether attributes
selected to define the strategies correctly detect the actions of the player. To study the
player strategies, we will… Mostrar más

In order to achieve the game flow and increase player retention, it is important that games
difficulty matches player skills. As a consequence, to evaluate how people play a game
is a crucial component, because detecting gamers strategies in video-games, it is possible
to fix the game difficulty. The main problem to detect the strategies is whether attributes
selected to define the strategies correctly detect the actions of the player. To study the
player strategies, we will use a Real Time Stategy (RTS) game. In a RTS the players make
use of units and structures to secure areas of a map and/or destroy the opponents resources.
In this work, we will extract the real-time information about the players strategies using
a platform base on the RTS game. After gathering information, the attributes that define
the player strategies are evaluated using unsupervised learning algorithm (K-Means and
Spectral Clustering). Finally, we will study the similitude among several gameplays where
players use different strategies. Mostrar menos