Reinforcement-Learning bei der Steuerung eines autonomen mobilen Roboters.
U. ZachmannKarsten BernsPublished in: Robotersysteme (1991)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- temporal difference
- state space
- dynamic programming
- markov decision processes
- model free
- learning algorithm
- information retrieval
- multi agent
- robot control
- machine learning
- perceptual aliasing
- markov decision process
- optimal policy
- neural network
- action selection
- optimal control
- learning problems
- control problems
- learning process
- temporal difference learning
- continuous state
- transition model
- relational reinforcement learning
- partially observable domains
- direct policy search