Unsupervised neural controller for Reinforcement Learning action-selection: Learning to represent knowledge

Constructing the correct Conceptual Graph representing some textual information requires a series of decisions, defined by vertex or edge creation. The process of creating Conceptual Graphs involves semiotics: the semantics, pragmatics and syntactics of the information, as well as graph structuralism and isomorphic projection, all described as decisions of a learning agent or system. The actual process taught from demonstrations of a human user, is known as Semantic Parsing, and is learnt by the agent through the novel fusion of Reinforcement Learning (RL) and Restricted Boltzmann Machines (RBM). Herein we showcase the design of such an agent in a theoretical manner, in order to define the background mechanisms which will learn how to parse information and correctly project it onto Conceptual Graphs.