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.



There are no comments yet.


page 1

page 2

page 3

page 4


Provably Efficient Exploration in Policy Optimization

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

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...

Stochastic Variance Reduction Methods for Policy Evaluation

Policy evaluation is a crucial step in many reinforcement-learning proce...

Offline Reinforcement Learning with Fisher Divergence Critic Regularization

Many modern approaches to offline Reinforcement Learning (RL) utilize be...

Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability

In the Bayesian reinforcement learning (RL) setting, a prior distributio...

Bi-directional Value Learning for Risk-aware Planning Under Uncertainty

Decision-making under uncertainty is a crucial ability for autonomous sy...

Kalman meets Bellman: Improving Policy Evaluation through Value Tracking

Policy evaluation is a key process in Reinforcement Learning (RL). It as...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.