Probabilistic Hyperproperties of Markov Decision Processes.
Rayna DimitrovaBernd FinkbeinerHazem TorfahPublished in: ATVA (2020)
Keyphrases
- markov decision processes
- optimal policy
- transition matrices
- state space
- reinforcement learning
- reachability analysis
- finite state
- policy iteration
- dynamic programming
- average cost
- infinite horizon
- decision theoretic planning
- probabilistic planning
- planning under uncertainty
- risk sensitive
- model based reinforcement learning
- probabilistic model
- average reward
- bayesian networks
- decision processes
- action space
- partially observable
- finite horizon
- factored mdps
- action sets
- markov decision process
- reinforcement learning algorithms
- multistage
- generative model
- learning algorithm
- initial state
- state and action spaces
- search space
- interval estimation