Log In Sign Up

Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems

by   Dhruv Malik, et al.

We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-quadratic systems, and study various settings of driving noise and reward feedback. We show that these methods provably converge to within any pre-specified tolerance of the optimal policy with a number of zero-order evaluations that is an explicit polynomial of the error tolerance, dimension, and curvature properties of the problem. Our analysis reveals some interesting differences between the settings of additive driving noise and random initialization, as well as the settings of one-point and two-point reward feedback. Our theory is corroborated by extensive simulations of derivative-free methods on these systems. Along the way, we derive convergence rates for stochastic zero-order optimization algorithms when applied to a certain class of non-convex problems.


page 1

page 2

page 3

page 4


Recent Theoretical Advances in Non-Convex Optimization

Motivated by recent increased interest in optimization algorithms for no...

Optimal rates for zero-order convex optimization: the power of two function evaluations

We consider derivative-free algorithms for stochastic and non-stochastic...

Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games

We study the global convergence of policy optimization for finding the N...

Derivative free optimization via repeated classification

We develop an algorithm for minimizing a function using n batched functi...

On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization

The problem of stochastic convex optimization with bandit feedback (in t...

Self-accelerating root search and optimisation methods based on rational interpolation

Iteration methods based on barycentric rational interpolation are derive...