Optimal model-free output synchronization of heterogeneous systems using off-policy reinforcement learning.
Hamidreza ModaresSubramanya P. NageshraoGabriel Alexandre Delgado LopesRobert BabuskaFrank L. LewisPublished in: Autom. (2016)
Keyphrases
- model free
- reinforcement learning
- heterogeneous systems
- reinforcement learning algorithms
- function approximation
- temporal difference
- average reward
- dynamic programming
- policy iteration
- distributed architecture
- rl algorithms
- optimal control
- policy evaluation
- state space
- computing systems
- markov decision processes
- multi agent
- application developers
- neural network
- data management
- information systems