A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs.
Mateo PerezFabio SomenziAshutosh TrivediPublished in: CoRR (2023)
Keyphrases
- learning algorithm
- sample complexity
- reinforcement learning
- markov decision processes
- linear temporal logic
- reinforcement learning algorithms
- temporal logic
- learning problems
- machine learning algorithms
- theoretical analysis
- model checking
- supervised learning
- state space
- machine learning
- vc dimension
- optimal policy
- factored mdps
- pac learning
- upper bound
- bounded model checking
- training data
- pac learning model
- linear time temporal logic
- generalization error
- active learning
- finite state
- average cost
- perceptron algorithm
- average reward
- classification noise
- decision theoretic planning
- uniform distribution
- training examples
- linear programming