Competition, Games and Evolution

There are multiple ways to approach Artificial Intelligence in relation to human or "natural" intelligence. At the center, the core aspect of behaviour characterizes the level of efficiency and adaptiveness to the environment, or how "intelligent" this behaviour looks like, regardless if it refers to human, animal or machine.
In this lecture, Natural Intelligence is explored under the fundamentals of Game Theory and Conflict Resolution. When resources are scarce and agents have to compete or cooperate in order to achive optimal outcomes, zero-sum and non-zero-sum games provide the mathematical tools to model the conflict situation and, sometimes, predict its evolution in the future. Simple setups like the "Chicken" or "Prisoner's Dilemma" games lead to extremely complex theory, involving the discovery of Evolutionary Stable Strategies like "T4T". Nevertheless, these are the bases for designing much simpler and practical applications in the scope of Swarm AI, like the Ant Colony Optimization (ACO) and similar optimization algorithms.

Keywords: Machine Learning, Data Analytics, AI, Artificial Intelligence, Game Theory, lecture
Video: https://youtu.be/6SDnjucD08E