How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning.
Rémi DromnelleErwan RenaudoGuillaume PourcelRaja ChatilaBenoît GirardMehdi KhamassiPublished in: CoRR (2020)
Keyphrases
- model free
- robot navigation
- reinforcement learning
- autonomous robots
- learning algorithm
- learning process
- real time
- learning tasks
- active learning
- autonomous mobile robot
- reinforcement learning algorithms
- function approximation
- linear combination
- machine learning
- artificial neural networks
- training data
- computer vision
- neural network