This paper addresses the problem of autonomous behaviors of virtual characters. We postulate that a behavior is regarded as autonomous when the actions performed by the agent result from the interaction between its internal dynamics and the environment, rather than being externally controlled. In this work, we argue that an autonomous behavior is an agent's solution to a given problem, which is obtained through a process of self-organization of the dynamics of a system that is composed of the agent's controller, its body and the environment. That process allows the emergence of complex behaviors without any description of actions or objectives. We show a technique capable of adapting an artificial neural network to consistently control virtual Khepera-like robots by means of simulated reproduction, with no measure of the robots' fitness. All the robots are either male or female, and they are capable of evolving different kinds of behaviors according to their own characteristics, guided solely by the environment's dynamics.

No abstract

No abstract

This paper presents an embodied open-ended environment driven evolutionary algorithm capable of evolving behaviors of autonomous agents without any explicit description of objectives, evaluation metrics or cooperative dynamics. The main novelty of our technique is obtaining intrinsically motivated autonomy of a virtual robot in continuous activity, by internalizing evolutionary dynamics in order to achieve adaptation of a neural controller, and with no need to frequently restart the agent's initial conditions as in traditional training methods. Our work is grounded on ideas from the enactive artificial intelligence field and the biological concept of enaction, from which it is argued that what makes a living being "intentional" is the ability to autonomously, adaptively rearrange their microstructure to suit some function in order to maintain its own constitution. We bring an alternative understanding of intrinsic motivation than that traditionally approached by intrinsic motivated reinforcement learning, and so we also make a brief discussion of the relationship between both paradigms and the autonomy of an agent. We show the autonomous development of foraging and navigation behaviors of a virtual robot.

No abstract