Reinforcement learning based on hierarchical temporal memory model

Kanonirs Georgijs

Modern reinforcement learning methods have a number of limitations imposed by the used artificial neural networks paradigm with a point neuron model. The use of the latest achievements of neuroscience within the theory of intelligence "The Thousand Brains Theory of Intelligence", as well as the application of the machine learning model "Hierarchical Temporal Memory" (HTM), which implements some aspects of this theory, have the potential both to develop already established reinforcement learning methods, and to create new approaches for solving this problem. The purpose of this work is to identify the prospects for using the HTM machine learning model in reinforcement learning.

Keywords:biologically-plausible machine learning methods, reinforcement learning, hierarchical temporal memory.