Multi-timescale nexting in a reinforcement learning robot.
Joseph ModayilAdam WhiteRichard S. SuttonPublished in: Adapt. Behav. (2014)
Keyphrases
- reinforcement learning
- robot control
- mobile robot
- real robot
- vision system
- path planning
- human robot interaction
- function approximation
- autonomous learning
- perceptual aliasing
- humanoid robot
- real time
- robot navigation
- state space
- robot behavior
- multi robot
- markov decision processes
- temporal difference
- reinforcement learning algorithms
- multi agent
- mobile robotics
- learning algorithm
- indoor environments
- computer vision
- manipulation tasks