New Ideas in Computational Neuroscience

Heuristics of Control: Habitization, Fragmentation, Memoization and Pruning

Intervenant(s)
Peter Dayan (Gatsby, UCL)
Informations pratiques
19 mai 2015
LNC2

Goal-directed or model-based control faces substantial computational challenges in deep planning problems. One popular solution to this is habitual or model-free control based on state-action values. In a simple planning task, we found evidence for three further heuristics: blinkered pruning of the decision-tree, the storage and direct reproduction of sequences of actions arising from search, and hierarchical decomposition. I will discuss models of these and their interactions. This is work with Quentin Huys in collaboration with Niall Lally, Jon Roiser and Sam Gershman.