Reinforcement Learning in MirrorBot.
Cornelius WeberDavid MuseMark ElshawStefan WermterPublished in: ICANN (1) (2005)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- state space
- function approximation
- temporal difference
- optimal control
- markov decision processes
- control problems
- robotic control
- neural network
- multi agent reinforcement learning
- model free
- optimal policy
- databases
- temporal difference learning
- robot control
- dynamic programming
- machine learning
- real time
- transfer learning
- supervised learning
- learning process
- multiscale
- learning algorithm
- reinforcement learning methods
- real world
- policy search
- direct policy search