A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers
This is an incremental improvement for cognitive modeling and robotics, using spiking neural networks to enhance temporal dynamics in reinforcement learning.
The paper tackled the problem of modeling cognitive phenomena by developing a Learning Classifier System with spiking neural networks as classifiers, which outperformed benchmark neural classifier systems and solved a robotic navigation task.
Learning Classifier Systems (LCS) are population-based reinforcement learners that were originally designed to model various cognitive phenomena. This paper presents an explicitly cognitive LCS by using spiking neural networks as classifiers, providing each classifier with a measure of temporal dynamism. We employ a constructivist model of growth of both neurons and synaptic connections, which permits a Genetic Algorithm (GA) to automatically evolve sufficiently-complex neural structures. The spiking classifiers are coupled with a temporally-sensitive reinforcement learning algorithm, which allows the system to perform temporal state decomposition by appropriately rewarding "macro-actions," created by chaining together multiple atomic actions. The combination of temporal reinforcement learning and neural information processing is shown to outperform benchmark neural classifier systems, and successfully solve a robotic navigation task.