Respective Advantages and Disadvantages of Model-based and Model-free Reinforcement Learning in a Robotics Neuro-inspired Cognitive Architecture.
Erwan RenaudoBenoît GirardRaja ChatilaMehdi KhamassiPublished in: BICA (2015)
Keyphrases
- advantages and disadvantages
- cognitive architecture
- model free reinforcement learning
- general intelligence
- robotic systems
- computational model
- information processing
- cognitive model
- cognitive architectures
- computational models
- artificial intelligence
- symbolic knowledge
- information foraging
- artificial neural networks
- neural network
- intelligent behavior
- symbolic representation
- computer vision
- thresholding methods
- vision system
- reinforcement learning
- policy gradient
- mental imagery
- human cognition
- tour guide robot
- database systems
- episodic memory
- machine intelligence
- multi agent
- function approximation