A model for general video game learning with HTM

Abstract

Abstract. A model-based agent, for general game playing in the context of Artificial General Intelligence is proposed. That agent is structured as an utility agent, that models the games through two functions, Transition and Reward. With these functions, a planning phase is proposed using a tree of actions. The agent is tested with two Atari games, Breakout and Pong.

Se propone un agente basado en modelos para el aprendizaje general de video juegos. El agente se estructura con dos funciones, de transición y de recompenza, que se usan en una fase de planeación. El modelo propuesto se prueba con dos juegos de Atari, Breakout y Pong.