Probabilistic opacity for Markov decision processes.
Béatrice BérardKrishnendu ChatterjeeNathalie SznajderPublished in: Inf. Process. Lett. (2015)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- reinforcement learning
- dynamic programming
- policy iteration
- planning under uncertainty
- transition matrices
- model based reinforcement learning
- reachability analysis
- reinforcement learning algorithms
- decision theoretic planning
- average reward
- action sets
- state and action spaces
- probabilistic planning
- decision processes
- action space
- finite horizon
- bayesian networks
- markov decision process
- infinite horizon
- probabilistic model
- risk sensitive
- average cost
- partially observable
- factored mdps
- generative model
- multistage
- decision diagrams
- partially observable markov decision processes
- discounted reward