Experimental Study of Reinforcement Learning in Mobile Robots Through Spiking Architecture of Thalamo-Cortico-Thalamic Circuitry of Mammalian Brain.
Vahid AzimiradMohammad Fattahi SaniPublished in: Robotica (2020)
Keyphrases
- experimental study
- basal ganglia
- action selection
- mobile robot
- reinforcement learning
- human brain
- connectionist models
- robot control
- biologically plausible
- path planning
- real robot
- management system
- experimental evaluation
- function approximation
- visual cortex
- motion planning
- temporal difference
- synthetic datasets
- autonomous robots
- network architecture
- optimal policy
- learning algorithm
- real time
- multi robot
- reinforcement learning algorithms
- obstacle avoidance
- dynamic environments
- event driven
- state space
- multi agent
- artificial neural networks
- unknown environments
- spike trains