Executive Function: A Contrastive Value Policy for Resampling and Relabeling Perceptions via Hindsight Summarization?. (arXiv:2204.12639v1 [cs.CL])

We develop the few-shot continual learning task from first principles and
hypothesize an evolutionary motivation and mechanism of action for executive
function as a contrastive value policy which resamples and relabels perception
data via hindsight summarization to minimize attended prediction error, similar
to an online prompt engineering problem. This is made feasible by the use of a
memory policy and a pretrained network with inductive biases for a grammar of
learning and is trained to maximize evolutionary survival. We show …

arxiv function policy summarization value