A Model of Fluid Intelligence based on Replay

Abstract

This paper proposes a model of rule/policy discovery based on sequential memory and its recall (replay). Fluid intelligence, as measured by intelligence tests, can be viewed as the ability to discover policies for solving problems from one or a small number of examples. To discover common rules from a small number of past time series, their memory and recall would be useful. The proposed model "goes over" recalled time series (replays) and extracts elements such as attributes, relationships among the input elements, and agent actions, to generate hypothetical policies.