Reinforcement Learning for Port-Hamiltonian Systems.
Olivier SprangersRobert BabuskaSubramanya P. NageshraoGabriel A. D. LopesPublished in: IEEE Trans. Cybern. (2015)
Keyphrases
- reinforcement learning
- computer systems
- temporal difference
- dynamic programming
- learning algorithm
- evolutionary algorithm
- neural network
- least squares
- data sets
- knowledge based systems
- constraint satisfaction problems
- learning systems
- complex systems
- markov decision processes
- function approximation
- computing systems
- real time