Recipe tuning by reinforcement learning in the SandS ecosystem.
Borja Fernández-GaunaManuel GrañaPublished in: CASoN (2014)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- learning algorithm
- model free
- state space
- fine tuning
- reinforcement learning algorithms
- optimal policy
- robotic control
- rule selection
- multi agent reinforcement learning
- parameter tuning
- optimal control
- learning process
- multi agent
- temporal difference
- markov decision process
- reinforcement learning methods
- real world
- parameter settings
- supervised learning
- decision trees
- artificial intelligence
- machine learning
- policy search
- data mining
- relational reinforcement learning