Detection-averse optimal and receding-horizon control for Markov decision processes.
Nan LiIlya V. KolmanovskyAnouck GirardPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- receding horizon
- optimal linear
- dynamic programming
- average cost
- air traffic control
- average reward
- optimal policy
- reinforcement learning
- finite horizon
- action sets
- optimal control
- state space
- finite state
- policy iteration
- formation control
- transition matrices
- infinite horizon
- control policy
- decision theoretic planning
- stationary policies
- action space
- markov decision process
- discounted reward
- control system
- unmanned aerial vehicles
- control method
- control strategy
- optimal solution