Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control.
Marco OlivaSoubarna BanikJosip JosifovskiAlois C. KnollPublished in: IJCNN (2022)
Keyphrases
- robot control
- neural network
- reinforcement learning
- inductive bias
- mobile robot
- autonomous robots
- machine learning
- inductive learning
- vision system
- real time
- neural network model
- fuzzy logic
- state space
- domain knowledge
- hypothesis space
- prior knowledge
- artificial neural networks
- domain theory
- model free
- genetic algorithm
- learning algorithm
- function approximation
- reinforcement learning algorithms
- pac learning