Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach.
Yingying LiYujie TangRunyu ZhangNa LiPublished in: IEEE Trans. Autom. Control. (2022)
Keyphrases
- derivative free
- linear quadratic
- optimal control
- reinforcement learning
- unconstrained optimization
- neural learning
- gradient method
- optimization methods
- closed loop
- control strategy
- dynamical systems
- nonlinear optimization
- optimization problems
- control system
- constrained optimization
- fan beam
- trust region
- learning algorithm
- optimization algorithm
- state space
- dynamic programming
- incremental learning
- vector valued
- multiresolution
- support vector
- objective function
- computer vision
- neural network