Global ETD Search

A Neuro-Symbolic Reinforcement Learning Architecture: Integrating Perception, Reasoning, and Control

Ellis, Hunter WayneVirginia Tech2025

… be seen as an adaptation of the Neuro-Symbolic Concept Learner[1] developed by IBM Wat- son, in which images and natural language are first processed by convolutional and residual neural networks, respectively, and then parsed by a symbolically reasoned program. Where the architecture proposed …

vt Repository record for A Neuro-Symbolic Reinforcement Learning Architecture: Integrating Perception, Reasoning, and Control (opens in a new tab)