Cognitive Science 0277 - Evolution of Game Playing

Evolutionary computation is an artificial intelligence strategy based on natural evolution, in which candidate solutions are evaluated and recombined based on their performance. Agent-based systems use a collection of information to solve a complex task, while possibly providing for planning, communication, error recovery, and learning. In this course we will study and combine these two techniques and apply them to virtual simulations of games such as Capture the Flag, Robocup, RoboRescue, Quidditch, and others. Emphasis is placed on the design and implementation of course projects. Students will be able to work with a variety of software packages, such as neural network simulators, evolutionary packages, virtual world simulators, computer game platforms such as pygames and Unity. Students should be comfortable programming in at least one high level programming language such as python, C, C++, C#, Java, Lisp, etc. Prerequisite detail: At least one college-level course in computer programming.

Mind, Brain, and Information Quantitative Skills Independent Work In this course, students are expected to spend around ten hours a week of preparation and work outside of class time. This time includes reading, writing, research, programming, and preparing for presentations.