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