Balancing detectability and performance of attacks on the control channel of Markov Decision Processes.
Alessio RussoAlexandre ProutièrePublished in: ACC (2022)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- decision theoretic planning
- transition matrices
- reinforcement learning
- dynamic programming
- decentralized control
- policy iteration
- model based reinforcement learning
- finite horizon
- risk sensitive
- planning under uncertainty
- markov decision process
- factored mdps
- reachability analysis
- control problems
- action space
- partially observable
- decision processes
- state and action spaces
- control system
- average cost
- control policies
- infinite horizon
- optimal control
- sufficient conditions
- reinforcement learning algorithms
- control strategy
- linear programming
- collaborative filtering