This paper studies how to balance evolutionary design and human expertise in order to best design situated autonomous agents which can learn speciic tasks. A genetic algorithm designs control circuits to learn simple behaviors, and given control strategies for simple behaviors, the genetic algorithm designs a combinational circuit that switches between these simple behaviors to perform a naviga...

This research examined the antecedents and consequences of identification with virtual teams. Specifically, we hypothesized that two structural characteristics (number of faceto-face meetings and task interdependence) and perceived quality of interaction (procedural and distributive justice) would be positively related to identification with the virtual team. A further hypothesis was that team ...

Inverse Reinforcement Learning (IRL) provides a powerful mechanism for learning complex behaviors from demonstration by rationalizing such demonstrations. Unfortunately its applicability has been largely hindered by lack of powerful representations that can take advantage of various task affordances while still admitting scalability. Inspired by the success of sampling based approaches in class...

This paper evaluates the Collective Neuro-Evolution (CONE) method, comparative to a related controller design method, in a simulated multi-robot system. CONE solves collective behavior tasks, and increases task performance via facilitating behavioral specialization. Emergent specialization is guided by genotype and behavioral specialization di erence metrics that regulate genotype recombination...

A key challenge in deploying teams of robots in real-world applications is to automate the control of teamwork, such that the designer can focus on the taskwork. Existing teamwork architectures seeking to address this challenge are monolithic, in that they commit to interaction protocols at the architectural level, and do not allow the designer to mix and match protocols for a given task. We pr...