Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon.
Ben HamblyRenyuan XuHuining YangPublished in: SIAM J. Control. Optim. (2021)
Keyphrases
- linear quadratic
- finite horizon
- optimal control
- infinite horizon
- policy gradient methods
- policy gradient
- closed loop
- average cost
- optimal policy
- vector valued
- dynamical systems
- dynamic programming
- natural actor critic
- markov decision processes
- reinforcement learning
- gaussian model
- control strategy
- robot arm
- markov decision process
- multistage
- state space
- partially observable