What's the Problem?Before discussing ways to prevent or cure problems with adaptive AI, we must first identify them. Picking out problems involves a combination of external observation and analysis of the internal workings of the system. No LearningSymptom: Learning does not occur, or happens inconsistently. Example: The decision tree for weapon selection usually selects the weakest weapon, despite better alternatives being available. Diagnostic: The model or the implementation is (partly) broken. Remedy:
UncontrollableSymptom: The learning does not match specific results, or degenerates over time. Example: The reinforcement learning animat does not retreat when it has low health, but instead attempts heroic attacks. Diagnostic: The system is not equipped to reliably provide the desired control. Remedy:
SuboptimalSymptom: Learning does not reach the perfect result. Example: The average error of a neural network used for target selection is high. Diagnostic: The design does not assist the adaptation; the system relies on optimality. Remedy:
UnrealisticSymptom: The behaviors are not realistic enough during the adaptation or at the end of the learning. Example: Learning to aim causes the animat to spin around in circles for a few seconds. Diagnostic: There is too much to learn; the policy is not designed for realism; the actions are inappropriate. Remedy:
|