Verification of General Markov Decision Processes by Approximate Similarity Relations and Policy Refinement.
Sofie HaesaertAlessandro AbatePaul M. J. Van den HofPublished in: QEST (2016)
Keyphrases
- markov decision processes
- optimal policy
- policy iteration
- policy evaluation
- markov decision process
- infinite horizon
- finite horizon
- average reward
- finite state
- factored mdps
- decision processes
- action space
- similarity relations
- dynamic programming
- partially observable
- average cost
- state and action spaces
- state space
- reinforcement learning
- reward function
- transition matrices
- reinforcement learning algorithms
- decision problems
- discounted reward
- decision theoretic planning
- markov decision problems
- model checking
- total reward
- partially observable markov decision processes
- learning rate
- continuous state spaces
- rough sets
- fuzzy logic
- machine learning