Abstract: In this paper, we applied online neuroevolution to evolve nonplayer characters for The Open Racing Car Simulator (TORCS). While previous approaches allowed online learning with performance ...

This is a project to reproduce the emergence of cognitive complexity through open-ended evolution of embodied agent populations in a 2D environment. Agents are controlled by evolvable neural ...

Neuroevolution has been used to develop applications such as reinforcement learning, artificial life, and artificial creativity. Some of the advantages of neuroevolution are that it can handle ...

Abstract: This paper addresses the challenge of learning to play many different video games with little domain-specific knowledge. Specifically, it introduces a neuroevolution approach to general ...

In my work across AI and cybersecurity, I've encountered few approaches with as much untapped potential as neuroevolution. This intersection of evolutionary biology and neural networks offers ...

Neuroevolution has been successfully used in developing controllers for phys- ical simulation domains. However, the ability to strategize in such domains has not been studied from an evolutionary ...

ESL This is the C# source code for the experiments with Egalitarian Social Learning (ESL) in a robot foraging domain. The re... 2012 UT^2: Winning Botprize 2012 Entry The Botprize Competition is an ...

Inspired by biological evolution processes, evolutionary computation employed at scale on CPU clusters has become one of the most effective approaches for training large neural networks. While the ...