Reinforcement Learning (Dagstuhl Seminar 13321).
Peter AuerMarcus HutterLaurent OrseauPublished in: Dagstuhl Reports (2013)
Keyphrases
- reinforcement learning
- function approximation
- machine learning
- temporal difference
- model free
- neural network
- robotic control
- temporal difference learning
- state space
- markov decision processes
- multi agent
- optimal control
- decision making
- learning capabilities
- multi agent reinforcement learning
- autonomous learning
- databases
- dynamic programming
- relational reinforcement learning
- policy search
- reinforcement learning methods
- genetic algorithm
- robot control
- reinforcement learning algorithms
- learning algorithm
- semi supervised