Using Q-Learning and Genetic Algorithms to Improve the Efficiency of Weight Adjustments for Optimal Control and Design Problems.
Kaivan KamaliL. J. JiangJohn YenK. W. WangPublished in: J. Comput. Inf. Sci. Eng. (2007)
Keyphrases
- optimal control
- reinforcement learning
- dynamic programming
- genetic algorithm
- feedback control
- control problems
- control strategy
- optimal control problems
- neural network
- risk sensitive
- class of nonlinear systems
- brownian motion
- state space
- actor critic
- evolutionary algorithm
- control law
- infinite horizon
- function approximation
- policy iteration
- multi objective
- linear programming
- credit assignment