Output regulation of unknown linear systems using average cost reinforcement learning.
Farnaz Adib YaghmaieSvante GunnarssonFrank L. LewisPublished in: Autom. (2019)
Keyphrases
- linear systems
- average cost
- markov decision processes
- reinforcement learning
- optimal policy
- sufficient conditions
- approximate dynamic programming
- optimal control
- dynamical systems
- control policy
- long run
- state space
- finite state
- infinite horizon
- policy iteration
- markov decision chains
- action sets
- finite number
- dynamic programming
- sparse linear systems
- markov decision process
- linear programming
- multistage
- risk sensitive
- coefficient matrix
- machine learning
- function approximation
- interior point methods
- linear program
- total cost
- action space
- markov decision problems
- learning algorithm
- model free
- mathematical model
- initial state