Multi-timescale Nexting in a Reinforcement Learning Robot
Joseph ModayilAdam WhiteRichard S. SuttonPublished in: CoRR (2011)
Keyphrases
- reinforcement learning
- mobile robot
- real robot
- robot control
- autonomous learning
- human robot interaction
- humanoid robot
- perceptual aliasing
- function approximation
- state space
- model free
- robotic control
- obstacle avoidance
- goal directed
- vision system
- learning algorithm
- indoor environments
- machine learning
- robot programming
- reinforcement learning algorithms
- policy search
- robotic systems
- path planning
- autonomous robots
- mobile robotics
- markov decision process
- formation control
- transfer learning
- search and rescue
- human robot
- robot arm
- optimal control
- action selection
- robot navigation
- multi robot
- position and orientation