Pith. sign in

REVIEW 1 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2105.11066 v4 pith:RJSCTGXD submitted 2021-05-24 cs.LG cs.ITmath.ITmath.OCstat.ML

classification cs.LGcs.ITmath.ITmath.OCstat.ML
keywords policyalgorithmdescentlearningmirrorregularizedregularizervalue
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Policy optimization, which finds the desired policy by maximizing value functions via optimization techniques, lies at the heart of reinforcement learning (RL). In addition to value maximization, other practical considerations arise 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 can often be accounted for via regularized RL, which augments the target value function with a structure-promoting regularizer. Focusing on discounted infinite-horizon Markov decision processes, we propose a generalized policy mirror descent (GPMD) algorithm for solving regularized RL. As a generalization of policy mirror descent (arXiv:2102.00135), our algorithm accommodates a general class of convex regularizers and promotes the use of Bregman divergence in cognizant of the regularizer in use. We demonstrate that our algorithm converges linearly to the global solution over an entire range of learning rates, in a dimension-free fashion, 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 appealing performance of GPMD.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 8 citations worldwide. Full citation record

  1. The Geometry of Nonlinear Reinforcement Learning

    cs.LG 2025-09 conditional novelty 5.0 of 10

    Actor-critic reinforcement learning methods are reformulated as mirror descent on the occupancy manifold, and a Hessian-based update is proposed for nonlinear and constrained objectives.

Pith tools