Intelligent agents are simulated agents that observe and interact with an environment. Their activity is usually directed towards achieving some goal, and they may use knowledge or learning to facilitate their success towards the goal. Any learning system that is encapsulated from its environment that it acts in can be considered an Intelligent Agent. Intelligent Agents can be used in simulations, games and robotics.
Keywords that describe the current research in the lab within the context of Intelligent Agents are: Life-Long Learning, Reinforcement Learning, Neuro-Evolution, and Particle Swarm Optimization.
As the realism in games continues to increase, through improvements in graphics and 3D engines, more focus is placed on the behavior of the simulated agents that inhabit the simulated worlds. The agents in modern video games must become more life-like in order to seem to belong in the environments they are portrayed in. Many modern artificial intelligence approaches achieve a high level of realism but this is accomplished through significant developer time spent scripting the behaviors of the Non-Playable Characters or NPC’s. These agents will behave in a believable fashion in the scenarios they have been programmed for, but do not have the ability to adapt to new situations. In this paper we introduce a modularized, real-time evolution training technique to evolve adaptable agents with life-like behaviors. Online performance during evolution is also improved by using selection mechanisms found in temporal difference learning methods to appropriately balance the exploration and exploitation of control policies. These methods are implemented and tested using the XNA framework producing very promising results regarding effi- ciency of techniques, and demonstrating many potential avenues for further research.
- John Reeder
- Michael Georgiopoulos
Evolutionary Computation journal is a journal published by MIT Press.
Evolutionary Computationprovides an international forum for facilitating and enhancing the exchange of information among researchers involved in both the theoretical and practical aspects of computational systems of an evolutionary nature.
The Transactions on Evolutionary Computation is published by IEEE.
This journal is devoted to the theory, design and applications of evolutionary computation, with emphasis given to engineering systems and scientific applications encompassing, but not limited to, evolutionary optimization, machine learning, intelligent systems design, image processing and machine vision, pattern recognition, evolutionary neurocomputing, evolutionary fuzzy systems, applications in biomedicine and biochemistry, robotics and control, mathematical modeling, civil, chemical, aeronautical, and industrial engineering applications.
The IEEE Transactions on Computational Intelligence and AI in Games (T-CIAIG) is published by IEEE.
T-CIAIG publishes peer-reviewed articles in computational intelligence and related areas in artificial intelligence applied to games. It has a broad scope and publishes high-quality papers on all aspects of computational intelligence and artificial intelligence related to games. This also includes video games, mathematical games, human-computer interactions in games, and games involving physical objects.
The AAAI (Association for the Advancement of Artificial Intelligence) Conference
This is the premier conference of the AAAI society, held annually, and one of the highest ranked AI conferences. The purpose of every AAAI conference venue is to promote research in AI and scientific exchange among AI researchers, practitioners, scientists, and engineers in related disciplines.
Conference on Evolutionary Computation
Considered a subfield of computational intelligence focused on combinatorial optimization problems, evolutionary computation is associated with systems that use computational models of evolutionary processes as the key elements in design and implementation, i.e. computational techniques which are based to some degree on the evolution of biological life in the natural world. A number of evolutionary computational models have been proposed, including evolutionary algorithms, genetic algorithms, the evolution strategy, evolutionary programming, and artificial life. This conference intends to be a major forum for scientists, engineers and practitioners interested in the study, analysis, design, modeling and implementation of evolvable systems, both theoretically and in a broad range of application fields.
GECCO (Genetic and Evolutionary Computation Conference)
The Genetic and Evolutionary Computation Conference (GECCO-2010) accepts the latest high-quality results in the growing field of genetic and evolutionary computation. Typical topics include: genetic algorithms, genetic programming, evolution strategies, evolutionary programming, real-world applications, learning classifier systems and other genetics-based machine learning, evolvable hardware, artificial life, adaptive behavior, ant colony optimization, swarm intelligence, biological applications, evolutionary robotics, coevolution, artificial immune systems.
Based on its impact factor, GECCO is 11th in the rankings of 701 international conferences in artificial intelligence, machine learning, robotics, and human-computer interaction.
AIIDE (Artificial Intelligence for Interactive Digital Entertainment Conference)
AIIDE is intended to be the definitive point of interaction between entertainment software developers interested in AI and academic and industrial AI researchers. AIIDE-10 includes invited speakers, research and industry presentations, project demonstrations, and product exhibits at its conferences. While traditionally emphasizing commercial computer and video games, researchers and developers are also invited to share their insights and cutting-edge results on all topics at the interface of entertainment and artificial intelligence, including serious games, entertainment robotics, and beyond.
Computational Intelligence in Games (CIG) Symposium
This conference is sponsored by IEEE.
Games have proven to be an ideal domain for the study of computational intelligence as not only are they fun to play and interesting to observe, but they provide competitive and dynamic environments that model many real-world problems. Additionally, methods from computational intelligence promise to have a big impact on game technology and development, assisting designers and developers and enabling new types of computer games. The Conferences on Computational Intelligence and Games bring together leading researchers and practitioners from academia and industry to discuss recent advances and explore future directions in this quickly moving field.
A python AI tool kit. Includes neural networks, support vector machines, and reinforcement learning algorithms. Comes integrated with some experimentation environments. It is useful for learning the concepts and quickly jumping into AI techniques.
A python toolkit for robotics.