Reinforcement-Learning enaktiv und inklusiv vermitteln.
Silvia JoachimMartin HenneckePublished in: INFOS (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- temporal difference
- robotic control
- learning algorithm
- state space
- machine learning
- clustering algorithm
- direct policy search
- action selection
- optimal policy
- learning problems
- supervised learning
- temporal difference learning
- perceptual aliasing
- transfer learning
- dynamic programming
- real time
- fitted q iteration
- database
- autonomous learning
- model free
- markov decision processes
- learning process
- multi agent