Learning Successor Features with Distributed Hebbian Temporal Memory

arXiv:2310.13391v2 Announce Type: replace
Abstract: This paper presents a novel approach to address the challenge of online temporal memory learning for decision-making under uncertainty in non-stationary, partially observable environments. The proposed algorithm, Distributed Hebbian Temporal Memory (DHTM), is based on factor graph formalism and a multicomponent neuron model. DHTM aims to capture sequential data relationships and make cumulative predictions about future observations, forming Successor Features (SF). Inspired by neurophysiological models of the neocortex, the algorithm utilizes distributed representations, sparse transition …

abstract algorithm arxiv challenge cs.ai cs.lg cs.ne decision distributed environments features graph making memory neuron novel observable paper temporal type uncertainty