Reinforcement Learning in a Neurally Controlled Robot Using Dopamine Modulated STDP.
Richard EvansPublished in: CoRR (2015)
Keyphrases
- reinforcement learning
- real robot
- temporal difference
- computer controlled
- robot control
- mobile robot
- perceptual aliasing
- action selection
- basal ganglia
- robot soccer
- function approximation
- autonomous learning
- model free
- human robot interaction
- multi robot
- robot navigation
- autonomous robots
- reinforcement learning algorithms
- learning algorithm
- human robot
- state space
- real time
- vision system
- experimental platform
- robot manipulators
- robot behavior
- motor control
- position and orientation
- humanoid robot
- markov decision processes
- motion planning
- simulated robot
- learning process
- optimal policy
- visual servoing
- indoor environments
- evaluation function
- transfer learning
- robotic systems
- unknown environments
- search and rescue
- multi agent
- decision making
- machine learning
- neural network