Robot Navigation using Reinforcement Learning and Slow Feature Analysis
Wendelin BöhmerPublished in: CoRR (2012)
Keyphrases
- robot navigation
- reinforcement learning
- continuous state
- autonomous mobile robot
- autonomous robots
- function approximation
- real time stereo
- scene understanding
- initially unknown
- landmark recognition
- state space
- map building
- function approximators
- markov decision processes
- model free
- dynamic programming
- topological map
- object recognition
- three dimensional
- learning algorithm
- real time
- transfer learning
- optimal policy
- mobile robot
- action selection
- feature selection