Probabilistic Opacity for Markov Decision Processes.
Béatrice BérardKrishnendu ChatterjeeNathalie SznajderPublished in: CoRR (2014)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- decision theoretic planning
- probabilistic planning
- policy iteration
- reinforcement learning
- reachability analysis
- dynamic programming
- planning under uncertainty
- probabilistic model
- factored mdps
- transition matrices
- finite horizon
- model based reinforcement learning
- decision processes
- bayesian networks
- average cost
- reinforcement learning algorithms
- partially observable
- action space
- infinite horizon
- state and action spaces
- discounted reward
- semi markov decision processes
- risk sensitive
- generative model
- markov decision process
- decision theoretic
- action sets
- monte carlo
- machine learning
- real time dynamic programming