Log In Sign Up

Approximate Midpoint Policy Iteration for Linear Quadratic Control

by   Benjamin Gravell, et al.

We present a midpoint policy iteration algorithm to solve linear quadratic optimal control problems in both model-based and model-free settings. The algorithm is a variation of Newton's method, and we show that in the model-based setting it achieves cubic convergence, which is superior to standard policy iteration and policy gradient algorithms that achieve quadratic and linear convergence, respectively. We also demonstrate that the algorithm can be approximately implemented without knowledge of the dynamics model by using least-squares estimates of the state-action value function from trajectory data, from which policy improvements can be obtained. With sufficient trajectory data, the policy iterates converge cubically to approximately optimal policies, and this occurs with the same available sample budget as the approximate standard policy iteration. Numerical experiments demonstrate effectiveness of the proposed algorithms.


page 16

page 17

page 19


Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √(T) Regret

We consider the task of learning to control a linear dynamical system un...

Structured Policy Iteration for Linear Quadratic Regulator

Linear quadratic regulator (LQR) is one of the most popular frameworks t...

Dual Policy Iteration

Recently, a novel class of Approximate Policy Iteration (API) algorithms...

Ternary Policy Iteration Algorithm for Nonlinear Robust Control

The uncertainties in plant dynamics remain a challenge for nonlinear con...

Reward-estimation variance elimination in sequential decision processes

Policy gradient methods are very attractive in reinforcement learning du...

Direct Policy Optimization using Deterministic Sampling and Collocation

We present an approach for approximately solving discrete-time stochasti...