Antonio J. Fernández-Leiva

A review of computational intelligence in RTS games

Real-time strategy games offer a wide variety of fundamental AI research challenges. Most of these challenges have applications outside the game domain. This paper provides a review on computational intelligence in real-time strategy games (RTS). It starts with challenges in real-time strategy games, then it reviews different tasks to overcome this challenges. Later, it describes the techniques used to solve this challenges and it makes a relationship between techniques and tasks. Finally, it presents a set of different frameworks used as test-beds for the techniques employed. This paper is intended to be a starting point for future researchers on this topic.

Ephemeral computing and bioinspired optimization: Challenges and opportunities

Computational devices with significant computing power are pervasive yet often under-exploited since they are frequently idle or performing non-demanding tasks. Exploiting this power can be a cost-effective solution for solving complex computational tasks. Device-wise, this computational power can some times comprise a stable, long-lasting availability windows but it will more frequently take the form of brief, ephemeral bursts, mainly in the presence of devices “lent” voluntarily by their users. A highly dynamic and volatile computational landscape emerges from the collective contribution of numerous such devices. Algorithms consciously running on these environments require specific properties in terms of flexibility, plasticity and robustness. Bioinspired algorithms are particularly well suited to this endeavor, thanks to their intrinsic features: decentralized functioning, intrinsic parallelism, resilience, and adaptiveness. The latter is essential to exert advanced self-control on the functioning and/or structure of the algorithm. Much has been done in providing self-adaptation capabilities to these techniques, yet the science of self-★ bionspired algorithms is still nascent, in particular regarding to higher-level self-adaptation, and self-management in the context of large scale optimization problems and distributed ephemeral computing technologies. Deploying bioinspired techniques on this scenario will also pave the way for the application of other techniques on this computational domain.

A procedural balanced map generator with self-adaptive complexity for the real-time strategy game planet wars

Procedural content generation (PCG) is the programmatic generation of game content using a random or pseudo-random process that results in an unpredictable range of possible gameplay spaces. This methodology brings many advantages to game developers, such as reduced memory consumption. This works presents a procedural balanced map generator for a real-time strategy game: Planet Wars. This generator uses an evolutionary strategy for generating and evolving maps and a tournament system for evaluating the quality of these maps in terms of their balance. We have run several experiments obtaining a set of playable and balanced maps.

Virtual player design using self-learning via competitive coevolutionary algorithms

The Google Artificial Intelligence (AI) Challenge is an international contest the objective of which is to program the AI in a two-player real time strategy (RTS) game. This AI is an autonomous computer program that governs the actions that one of the two players executes during the game according to the state of play. The entries are evaluated via a competition mechanism consisting of two-player rounds where each entry is tested against others. This paper describes the use of competitive coevolutionary (CC) algorithms for the automatic generation of winning game strategies in Planet Wars, the RTS game associated with the 2010 contest. Three different versions of a prime algorithm have been tested. Their common nexus is not only the use of a Hall-of-Fame (HoF) to keep note of the winners of past coevolutions but also the employment of an archive of experienced players, termed the hall-of-celebrities (HoC), that puts pressure on the optimization process and guides the search to increase the strength of the solutions; their differences come from the periodical updating of the HoF on the basis of quality and diversity metrics. The goal is to optimize the AI by means of a self-learning process guided by coevolutionary search and competitive evaluation. An empirical study on the performance of a number of variants of the proposed algorithms is described and a statistical analysis of the results is conducted. In addition to the attainment of competitive bots we also conclude that the incorporation of the HoC inside the primary algorithm helps to reduce the effects of cycling caused by the use of HoF in CC algorithms.

On user-centric memetic algorithms

Memetic algorithms (MAs) constitute a metaheuristic optimization paradigm [usually based on the synergistic combination of an evolutionary algorithm (EA) and trajectory-based optimization techniques] that systematically exploits the knowledge about the problem being solved and that has shown its efficacy to solve many combinatorial optimization problems. However, when the search depends heavily on human-expert’s intuition, the task of managing the problem knowledge might be really difficult or even indefinable/impossible; the so-called interactive evolutionary computation (IEC) helps to mitigate this problem by enabling the human user to interact with an EA during the optimization process. Interactive MAs can be constructed as reactive models in which the MA continuously demands the intervention of the human user; this approach has the drawback that provokes fatigue to the user. This paper considers user-centric MAs, a more global perspective of interactive MAs since it hints possibilities for the system to be proactive rather than merely interactive, i.e., to anticipate some of the user behavior and/or exhibit some degree of creativity, and provides some guidelines for the design of two different models for user-centric MAs, namely reactive and proactive search-based schema. An experimental study over two complex NP-hard problems, namely the Traveling Salesman problem and a Gene Ordering Problem, shows that user-centric MAs are in general effective optimization methods although the proactive approach provides additional advantages.

Solving the tool switching problem with memetic algorithms

Abstract The tool switching problem (ToSP) is well known in the domain of flexible manufacturing systems. Given a reconfigurable machine, the ToSP amounts to scheduling a collection of jobs on this machine (each of them requiring a different set of tools to be completed), as well as the tools to be loaded/unloaded at each step to process these jobs, such that the total number of tool switches is minimized. Different exact and heuristic methods have been defined to deal with this problem. In this work, we focus on memetic approaches to this problem. To this end, we have considered a number of variants of three different local search techniques (hill climbing, tabu search, and simulated annealing), and embedded them in a permutational evolutionary algorithm. It is shown that the memetic algorithm endowed with steepest ascent hill climbing search yields the best results, performing synergistically better than its stand-alone constituents, and providing better results than the rest of the algorithms (including those returned by an effective ad hoc beam search heuristic defined in the literature for this problem).

On balance and dynamism in procedural content generation with self-adaptive evolutionary algorithms

We consider search-based procedural content generation in the context of Planet Wars, an RTS game. The objective of this work is to generate maps for the aforementioned game, that result in an interesting game-play. In order to characterize interestingness we focus on the properties of balance and dynamism. The former captures the fact that no player is overwhelmed by the opponent during the game, whereas the latter tries to model the fact that there is a lot of action during the game. To measure these properties on a given map, we conduct several games on them using top AI bots and collect statistics which are, in turn, used as inputs of a fuzzy rule base. This system is embedded within an evolutionary algorithm that features self-adaptation of mutation parameters as well as variable-length chromosomes (thus implying maps of different sizes). The experimentation focuses both on the optimization of balance and dynamism as stand-alone properties and in the analysis of the different tradeoffs attainable through them. To reach this goal a multi objective approach is used. We analyze both the usefulness of map-size self-adaptation in each scenario, as well as the properties of maps leading to different tradeoffs between dynamism and balance.

Bio-inspired combinatorial optimization: notes on reactive and proactive interaction

Evolutionary combinatorial optimization (ECO) is a branch of evolutionary computing (EC) focused on finding optimal values for combinatorial problems. Algorithms ranging in this category require that the user defines, before the process of evolution, the fitness measure (i.e., the evaluation function) that will be used to guide the evolution of candidate solutions. However, there are many problems that possess aesthetical or psychological features and as a consequence fitness evaluation functions are difficult, or even impossible, to formulate mathematically. Interactive evolutionary computation (IEC) has recently been proposed as a part of EC to cope with this problem and its classical version basically consists of incorporating human user evaluation during the evolutionary procedure. This is however not the only way that the user can influence the evolution in IEC and currently one can find that IEC has been been successfully deployed on a number of hard combinatorial optimization problems. This work examines the application of IEC to these problems. We describe the basic fundament of IEC, present some guidelines to the design of interactive evolutionary algorithms (IEAs) to handle combinatorial optimization problems, and discuss the two main models over which IEC is constructed, namely reactive and proactive searchbased schemas. An overview of the existing literature on the topic is also provided. We conclude with some reflections on the lessons learned, and the future directions that research might take in this area.

Memetic cooperative models for the tool switching problem

This work deals with memetic-computing agent-models based on the cooperative integration of search agents endowed with (possibly different) optimization strategies, in particular memetic algorithms. As a proof-of-concept of the model, we deploy it on the tool switching problem (ToSP), a hard combinatorial optimization problem that arises in the area of flexible manufacturing. The ToSP has been tackled by different algorithmic methods ranging from exact to heuristic methods (including local search meta-heuristics, population-based techniques and hybrids thereof, i.e., memetic algorithms). Here we consider an ample number of instances of this cooperative memetic model, whose agents are adapted to cope with this problem. A detailed experimental analysis shows that the meta-models promoting the cooperation among memetic algorithms provide the best overall results compared with their constituent parts (i.e., memetic algorithms and local search approaches). In addition, a parameter sensitivity analysis of the meta-models is developed in order to understand the interplay among the elements of the proposed topologies.

Procedural Content Generation for Real-Time Strategy Games

Videogames are one of the most important and profitable sectors in the industry of entertainment. Nowadays, the creation of a videogame is often a large-scale endeavor and bears many similarities with, e.g., movie production. On the central tasks in the development of a videogame is content generation, namely the definition of maps, terrains, non-player characters (NPCs) and other graphical, musical and AI-related components of the game. Such generation is costly due to its complexity, the great amount of work required and the need of specialized manpower. Hence the relevance of optimizing the process and alleviating costs. In this sense, procedural content generation (PCG) comes in handy as a means of reducing costs by using algorithmic techniques to automatically generate some game contents. PCG also provides advantages in terms of player experience since the contents generated are typically not fixed but can vary in different playing sessions, and can even adapt to the player herself. For this purpose, the underlying algorithmic technique used for PCG must be also flexible and adaptable. This is the case of computational intelligence in general and evolutionary algorithms in particular. In this work we shall provide an overview of the use of evolutionary intelligence for PCG, with special emphasis on its use within the context of real- time strategy games. We shall show how these techniques can address both playability and aesthetics, as well as improving the game AI. PURRED on by the emergence of the videogame industry as the main component of the entertainment industry has motivated, research on videogames has acquired increasing notoriety during the last years. Such research spans many areas such as marketing and gamification, psychology and player satisfaction, computational intelligence, education and health (serious games) and computer graphics, just to cite a few. This diversification of research areas is largely motivated by a shift in the priorities of the video game industry: while games used to rely heavily on their graphical quality, other features such as the music, the player immersion into the game and interesting storyline have gained enormous importance. To cope with the plethora of new interesting challenges in the area of