Convergence of Policy Gradient Methods for Finite-Horizon Exploratory Linear-Quadratic Control Problems.
Michael GiegrichChristoph ReisingerYufei ZhangPublished in: SIAM J. Control. Optim. (2024)
Keyphrases
- optimal control
- control problems
- infinite horizon
- linear quadratic
- finite horizon
- average cost
- dynamic programming
- reinforcement learning
- optimal policy
- control strategy
- partially observable
- brownian motion
- control law
- multistage
- reinforcement learning methods
- convergence rate
- markov decision processes
- markov decision process
- policy iteration
- control system
- bayesian networks