Dateneffizientes Reinforcement-Learning.
Volkmar SterzingSteffen UdluftPublished in: Künstliche Intell. (2009)
Keyphrases
- reinforcement learning
- function approximation
- optimal control
- markov decision processes
- model free
- learning algorithm
- knowledge base
- temporal difference learning
- learning process
- state space
- control problems
- reinforcement learning algorithms
- temporal difference
- learning problems
- optimal policy
- multi agent
- action space
- function approximators
- continuous state
- real time
- autonomous learning
- markov decision process
- sufficient conditions
- hidden markov models
- objective function
- computer vision
- machine learning