Policy Synthesis for Switched Linear Systems With Markov Decision Process Switching.
Bo WuMurat CubuktepeFranck DjeumouZhe XuUfuk TopcuPublished in: IEEE Trans. Autom. Control. (2023)
Keyphrases
- markov decision process
- linear systems
- optimal policy
- state space
- sufficient conditions
- dynamical systems
- markov decision processes
- finite horizon
- reinforcement learning
- infinite horizon
- policy iteration
- initial state
- coefficient matrix
- sparse linear systems
- dynamic programming
- transition probabilities
- reward function
- pid controller
- real time
- machine learning
- finite state
- average cost
- multistage
- multi objective
- artificial neural networks
- learning algorithm
- action space
- neural network