Policy Iteration Algorithm for Optimal Control of Stochastic Logical Dynamical Systems.
Yuhu WuTielong ShenPublished in: IEEE Trans. Neural Networks Learn. Syst. (2018)
Keyphrases
- dynamical systems
- policy iteration algorithm
- optimal control
- reinforcement learning
- partially observable markov decision processes
- infinite horizon
- actor critic
- policy iteration
- finite state
- markov decision processes
- state space
- optimal control problems
- fixed point
- linear quadratic
- dynamic programming
- control problems
- differential equations
- control theory
- markov chain
- partially observable
- control law
- control strategy
- linear systems
- average cost
- reinforcement learning methods
- optimal policy
- model free
- markov decision process
- stochastic control
- single agent
- policy gradient
- approximate dynamic programming