Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

by   Wenhao Zhan, et al.

Policy optimization, which learns the policy of interest by maximizing the value function via large-scale optimization techniques, lies at the heart of modern reinforcement learning (RL). In addition to value maximization, other practical considerations arise commonly as well, including the need of encouraging exploration, and that of ensuring certain structural properties of the learned policy due to safety, resource and operational constraints. These considerations can often be accounted for by resorting to regularized RL, which augments the target value function with a structure-promoting regularization term. Focusing on an infinite-horizon discounted Markov decision process, this paper proposes a generalized policy mirror descent (GPMD) algorithm for solving regularized RL. As a generalization of policy mirror descent Lan (2021), the proposed algorithm accommodates a general class of convex regularizers as well as a broad family of Bregman divergence in cognizant of the regularizer in use. We demonstrate that our algorithm converges linearly over an entire range of learning rates, in a dimension-free fashion, to the global solution, even when the regularizer lacks strong convexity and smoothness. In addition, this linear convergence feature is provably stable in the face of inexact policy evaluation and imperfect policy updates. Numerical experiments are provided to corroborate the applicability and appealing performance of GPMD.


page 1

page 2

page 3

page 4


On the connection between Bregman divergence and value in regularized Markov decision processes

In this short note we derive a relationship between the Bregman divergen...

Provably Efficient Exploration in Policy Optimization

While policy-based reinforcement learning (RL) achieves tremendous succe...

On the Convergence Rates of Policy Gradient Methods

We consider infinite-horizon discounted Markov decision problems with fi...

Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes

We present new policy mirror descent (PMD) methods for solving reinforce...

A Novel Framework for Policy Mirror Descent with General Parametrization and Linear Convergence

Modern policy optimization methods in applied reinforcement learning, su...

On the Convergence of Policy in Unregularized Policy Mirror Descent

In this short note, we give the convergence analysis of the policy in th...

L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning

This paper proposes a new regularization technique for reinforcement lea...

Please sign up or login with your details

Forgot password? Click here to reset