Maze Learning using a Hyperdimensional Predictive Processing Cognitive Architecture

TL;DR

This paper introduces CogNGen, a neurobiologically-inspired cognitive architecture combining predictive processing and hyperdimensional models, capable of learning and performing maze tasks with performance comparable to deep reinforcement learning.

Contribution

The paper presents CogNGen, a novel cognitive architecture that bridges high-level symbolic and low-level neurobiological models for scalable, continual learning and human-like performance.

Findings

CogNGen matches deep reinforcement learning in maze tasks.

CogNGen outperforms in memory-specific maze tasks.

Supports scalable, continual learning.

Abstract

We present the COGnitive Neural GENerative system (CogNGen), a cognitive architecture that combines two neurobiologically-plausible, computational models: predictive processing and hyperdimensional/vector-symbolic models. We draw inspiration from architectures such as ACT-R and Spaun/Nengo. CogNGen is in broad agreement with these, providing a level of detail between ACT-R's high-level symbolic description of human cognition and Spaun's low-level neurobiological description, furthermore creating the groundwork for designing agents that learn continually from diverse tasks and model human performance at larger scales than what is possible with current systems. We test CogNGen on four maze-learning tasks, including those that test memory and planning, and find that CogNGen matches performance of deep reinforcement learning models and exceeds on a task designed to test memory.