Towards Min Max Generalization in Reinforcement Learning.
Raphael FonteneauSusan A. MurphyLouis WehenkelDamien ErnstPublished in: ICAART (Revised Selected Papers) (2010)
Keyphrases
- min max
- reinforcement learning
- multiobjective optimization
- function approximation
- max min
- machine learning
- learning algorithm
- optimal policy
- dynamic programming
- transition model
- markov decision processes
- supervised learning
- database
- hidden markov models
- search algorithm
- multi agent
- data mining
- data sets
- state space
- control system
- learning process
- learning capabilities