A model of empathy for artificial agent teamwork.

This thesis introduces a model of empathy as a basis for helpful behaviour in teams consisting purely of artificial agents that collaborate on practical problem-solving tasks, and investigates whether the performance of such teams can benefit from empathic help between members as the analogy with human teams might suggest. Guided by existing models of natural empathy in psychology and neuroscience, it identifies the potential empathy factors for artificial agents, as well as the mechanisms by which they produce affective and behavioural responses. The performance of empathic agent teams situated in a microworld similar to the Coloured Trails game is studied through simulation experiments, with the model parameters optimized by a genetic algorithm. For low to moderate levels of random disturbance in the environment, empathic help is superior to random help, and it outperforms rational help as rational decision complexity grows, in particular at higher levels of environmental disturbance. --P. ii.