Policy Synthesis for Switched Linear Systems with Markov Decision Process Switching.
Bo WuMurat CubuktepeFranck DjeumouZhe XuUfuk TopcuPublished in: CoRR (2020)
Keyphrases
- markov decision process
- linear systems
- state space
- optimal policy
- dynamical systems
- sufficient conditions
- markov decision processes
- reinforcement learning
- finite horizon
- infinite horizon
- policy iteration
- coefficient matrix
- sparse linear systems
- initial state
- transition probabilities
- reward function
- decision problems
- average cost
- interior point methods
- action space
- machine learning
- real time
- dynamic programming