The usage of broad sets of training data is paramount to evolve adaptive agents. In this
respect, competitive co-evolution is a widespread technique in which the coexistence of …

Neuroevolution, ie evolution of artificial neural networks, has recently emerged as a
powerful technique for solving challenging reinforcement learning problems. Compared to …

Understanding how evolutionary agents behave in complex environments is a challenging
problem. Agents can be faced with complex fitness landscapes derived from multi-stage …

While neuroevolution has been used successfully to discover effective control policies for
intelligent agents, it has been difficult to evolve behavior that is multimodal, ie consists of …

Traditional industrial robotics is primarily focused on optimal path control. In contrast,
modern robotic tasks increasingly require a greater degree of adaptability and flexibility to …

I Eg Q-learning, Temporal Differences I Generate targets through prediction errors I Learn
when successive predictions differ I Predictions represented as a value function I Values of …

Evolving agents to learn how to solve complex, multi-stage tasks to achieve a goal is a
challenging problem. Problems such as the River Crossing Task are used to explore how …

Nature has discovered how to evolve intelligent systems, but our current deep learning
methods rely on a great deal of manual configuration and human oversight …

Keepaway is a simpler subtask of robot soccer where three keepers' attempt to keep
possession of the ball while a taker'tries to steal it from them. This is a less complex task than …

The complexity of cooperative behavior is a crucial issue in multiagent-based social
simulation. In this paper, an agent-based model is proposed to study the evolution of …