Scenario-Based Verification of Uncertain MDPs.
Murat CubuktepeNils JansenSebastian JungesJoost-Pieter KatoenUfuk TopcuPublished in: TACAS (1) (2020)
Keyphrases
- markov decision processes
- reinforcement learning
- state space
- decision making
- model checking
- planning under uncertainty
- dynamic programming
- factored mdps
- asynchronous circuits
- face verification
- formal methods
- policy iteration
- markov decision problems
- finite horizon
- markov decision process
- incomplete information
- optimal policy
- formal verification
- learning algorithm
- probabilistic planning
- verification method
- decision theoretic planning
- model based reinforcement learning
- real time dynamic programming