Credit assignment in AI is about working out which which rule or parameter should be given the credit (or blame) when something works well or badly. This is important to enable the syetm to learn, by reinforcing good rules. However, this can be hard when several rules are involved, hence one of the reaosn for explanation-based learning. It can be especially difficult in reinformcement learning as the reward may occur sometime after the crirtial action with other actiosn in between. For example, if you take a wrong turn early in a journey it may be some time before you realise, but the last few navigation chocies may nave been reasonable – it is the first choice that should be given the 'credit' ( this case approbation).
Defined on page 379
Used on pages 103, 379
Also known as credit assignment problem