Balancing detectability and performance of attacks on the control channel of Markov Decision Processes.
Alessio RussoAlexandre ProutièrePublished in: CoRR (2021)
Keyphrases
- markov decision processes
- optimal policy
- state space
- transition matrices
- finite state
- decentralized control
- reinforcement learning
- decision theoretic planning
- finite horizon
- policy iteration
- planning under uncertainty
- partially observable
- model based reinforcement learning
- factored mdps
- infinite horizon
- dynamic programming
- action sets
- control system
- markov decision process
- image quality
- average reward
- reinforcement learning algorithms
- optimal control
- action space
- risk sensitive
- average cost
- reachability analysis
- state abstraction
- control problems
- state and action spaces
- real time dynamic programming