Article

Building Goal-Directed Cognitive Graphs

2026-02-19

Abstract excerpt

Flexible behavior requires building internal structured models from experience to support goal-directed action. Although environmental transition statistics accumulate gradually, how they are used to construct a compact goal-directed graph remains unclear. We introduce the Sparse Cognitive Graph (SCG), a reinforcement-learning framework that separates gradual transition learning from the sparse directed graph that...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: b9b85151-7f71-5e6b-8dda-3c7c21d7881a
DOI: 10.64898/2026.02.18.706628

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Building Goal-Directed Cognitive GraphsDOI 10.64898/2026.02.18.706628Read

Trial-by-trial learning of successor representations in human behaviorSemantic proximity Read

A surprising link between cognitive maps, successor-relation based reinforcement learning, and BTSPSemantic proximity Read

Learning Structures: Predictive Representations, Replay, and GeneralizationSemantic proximity Read

Searching for rewards in graph-structured spacesSemantic proximity Read

How Humans Restructure Predictive Models: Context-Tree Dynamics in Sequential LearningSemantic proximity Read

Goals as dynamical attractors: a momentum-based account of stable and flexible goal commitmentSemantic proximity Read

Transferring structural knowledge across cognitive maps in humans and modelsSemantic proximity Read

Computational neural mechanisms of goal-directed planning and problem solvingSemantic proximity Read

Flexible route planning and rapid structure learning by mice in complex environmentsSemantic proximity Read

Reinforcement Learning approaches to hippocampus-dependent flexible spatial navigationSemantic proximity Read

Simple Plans or Sophisticated Habits? State, Transition and Learning Interactions in the Two-step TaskSemantic proximity Read

Humans can navigate complex graph structures acquired during latent learningSemantic proximity Read