Asymptotic Security by Model-based Incident Handlers for Markov Decision Processes.
Hampei SasaharaHenrik SandbergPublished in: CDC (2021)
Keyphrases
- markov decision processes
- finite state
- interval estimation
- state space
- reinforcement learning
- optimal policy
- dynamic programming
- decision theoretic planning
- policy iteration
- reachability analysis
- average cost
- reinforcement learning algorithms
- factored mdps
- risk sensitive
- transition matrices
- decision processes
- information security
- partially observable
- planning under uncertainty
- action sets
- average reward
- action space
- markov decision process
- finite horizon
- semi markov decision processes
- model free
- security issues
- state and action spaces
- model based reinforcement learning
- infinite horizon
- real time dynamic programming