Improved Iterative Methods for Verifying Markov Decision Processes.
Jaber KarimpourAyaz IsazadehMohammadSadegh MohagheghiKhayyam SalehiPublished in: FSEN (2015)
Keyphrases
- markov decision processes
- iterative methods
- state space
- optimal policy
- finite state
- reinforcement learning
- dynamic programming
- transition matrices
- decision theoretic planning
- policy iteration
- image reconstruction from projections
- reachability analysis
- average cost
- action space
- partially observable
- constrained optimization
- planning under uncertainty
- reinforcement learning algorithms
- infinite horizon
- finite horizon
- average reward
- factored mdps
- markov decision process
- model based reinforcement learning
- machine learning
- iterative algorithms
- neural network
- computationally expensive