Quasi-online Reinforcement Learning for Robots.
Bram BakkerViktor ZhumatiyGabriel GruenerJürgen SchmidhuberPublished in: ICRA (2006)
Keyphrases
- reinforcement learning
- online learning
- robotic control
- cooperative
- robot control
- real time
- reinforcement learning algorithms
- markov decision processes
- function approximation
- multi agent
- machine learning
- real robot
- humanoid robot
- robotic systems
- multi robot
- supervised learning
- human robot interaction
- dynamic programming
- social media
- learning process
- service robots
- multi robot systems
- policy search
- robotic agents
- artificial intelligence