Learning-Based Mean-Payoff Optimization in an Unknown MDP under Omega-Regular Constraints.
Jan KretínskýGuillermo A. PérezJean-François RaskinPublished in: CoRR (2018)
Keyphrases
- mobile devices
- mobile learning
- neural network
- learning process
- supervised learning
- background knowledge
- constraint satisfaction
- global optimization
- reinforcement learning
- prior knowledge
- optimization problems
- sufficient conditions
- optimization algorithm
- learning tasks
- incomplete information
- constrained optimization