Multi-timescale Nexting in a Reinforcement Learning Robot.
Joseph ModayilAdam WhiteRichard S. SuttonPublished in: SAB (2012)
Keyphrases
- reinforcement learning
- mobile robot
- real robot
- robot control
- autonomous learning
- autonomous robots
- function approximation
- robot arm
- reinforcement learning algorithms
- markov decision processes
- vision system
- learning algorithm
- model free
- human robot interaction
- mobile robotics
- perceptual aliasing
- simulated robot
- robot behavior
- computer vision
- multi agent
- state space
- optimal policy
- goal directed
- path planning
- supervised learning
- temporal difference
- markov decision process
- position and orientation
- robot navigation
- robot soccer
- end effector
- service robots
- search and rescue
- neural network