Maze Learning using a Hyperdimensional Predictive Processing Cognitive Architecture
This work addresses the challenge of creating scalable, human-like cognitive agents for tasks like maze learning, though it appears incremental by building on existing architectures like ACT-R and Spaun.
The authors tackled the problem of designing a cognitive architecture for maze learning by combining predictive processing and hyperdimensional models, resulting in CogNGen, which matches deep reinforcement learning performance and exceeds it on a memory task.
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.