eess.SYMay 26, 2026

Sample Complexity of Policy Gradient for Log-Growth Control

Authors: Qiuhua PanYukai ShenLiwei ZhangCailian ChenXinping Guan

Organizations: State Key Laboratory of Submarine Geoscience, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China · Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China · Shanghai Key Laboratory of Perception and Control in Industrial Network Systems, Shanghai 200240, China · Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai 200240, China

Abstract

We study the sample complexity of policy gradient for log-growth control -- the problem of learning, from observed state transitions, a feedback gain that optimally stabilizes a scalar linear system driven through a multiplicative-noise actuation channel. The objective J(K)=E[log1+BK]J(K) = \mathbb{E}[\log|1+BK|] is the top Lyapunov exponent of the closed loop. This problem carries a structural difficulty we call the cusp obstruction: the optimal gain KK^* always places the noise singularity bsing(K)=1/Kb_{\rm sing}(K) = -1/K in the interior of the support. At this singular optimum the policy gradient exists only as a Cauchy principal value, not as a Lebesgue integral, and the natural single-sample gradient estimator has infinite variance. Standard first-order stochastic-optimization analysis is thus inapplicable at the optimum, and merely smoothing the objective does not resolve the difficulty. The obstruction, however, has an exploitable symmetry: the Cauchy kernel is an odd function of the displacement from the moving pole, so pairing each observation with its reflection through the pole cancels the divergent part. This one cancellation simultaneously controls the population curvature, the gradient-estimator variance, and the bias incurred when the noise density is estimated. Combining these bounds with a closed-form single-transition gradient oracle, we prove that projected mini-batch policy gradient, initialized in any compact subset of the stabilizing region, attains total sample complexity O~(1/η)\tilde{O}(1/η) when the noise density is known and O~(η(2s+1)/(2s))\tilde{O}(η^{-(2s+1)/(2s)}) when it must be estimated, for CsC^s noise densities with s2s \geq 2.

Explore similar work

Aug 7, 2026math.OC

Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control

Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space. We study entropy-regularized discounted linear-quadratic (LQ) control. A Bellman verification argument shows that the unrestricted problem has a linear-Gaussian optimal policy, and the discounted-occupancy-weighted statewise Wasserstein gradient is tangent to this policy class. WPG therefore reduces exactly to a finite-dimensional ODE for the feedback gain and action covariance. We prove that this ODE is globally well posed and converges exponentially from every admissible initialization. For each fixed LQ problem, the exponent has a positive limit as the entropy temperature tends to zero and contains no perturbative factor of the form exp(c/τ)\exp(-c/τ), while retaining the usual dependence on the conditioning of the control problem.
Zhaoyu Zhu, Rui Gao, Shuang Li
Jun 3, 2026cs.LG

Policy Gradient for Continuous-Time Robust Markov Decision Processes

The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context. This paper investigates policy gradient algorithms within a continuous-time RMDP framework. Policy gradients and adversarial gradients are derived using pathwise and adjoint-based formulas for stochastic and ordinary differential equations. We propose double-loop optimisers to obtain linear convergence in the oracle-based setting and an O~(1ε2)\tilde{\mathcal{O}}(\frac{1}{ε^2}) sample complexity in the sample-based setting in an analysis which also derives novel tools for the framework of undiscounted total cost MDPs. Additionally, we propose mean-field optimisers as distributional optimisers with an O~(1K)\tilde{\mathcal{O}}(\frac{1}{K}) oracle-based convergence rate and an O~(N2ε)\tilde{\mathcal{O}}(\frac{N^2}ε) sample complexity under NN-particle approximation. The effectiveness of continuous-time policy gradient algorithms is confirmed for both optimisers on continuous-time RMDPs with neural ordinary differential equation dynamics.
Tanya Veeravalli, David M. Bossens, Atsushi Nitanda
May 13, 2026cs.LG

Achieving ε^{-2} Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions

In this paper, we establish last-iterate convergence rates for off-policy actor--critic methods in reinforcement learning. In particular, under a single-loop, single-timescale implementation and a broad class of policy updates, including approximate policy iteration and natural policy gradient methods, we prove the first O~(ε2)\tilde{\mathcal{O}}(ε^{-2}) sample complexity guarantee for finding an εε-optimal policy under minimal assumptions, namely, the existence of a policy that induces an irreducible Markov chain. This stands in stark contrast to the existing literature, where an O~(ε2)\tilde{\mathcal{O}}(ε^{-2}) sample complexity is achieved only through nested-loop updates and/or under strong, algorithm-dependent assumptions on the policies, such as uniform mixing and uniform exploration. Technically, to address the challenges posed by the coupled update equations arising from the single-loop implementation, as well as the potentially unbounded iterates induced by off-policy learning, our analysis is based on a coupled Lyapunov drift framework. Specifically, we establish a geometric convergence rate for the actor and an O~(1/T)\tilde{\mathcal{O}}(1/T) convergence rate for the critic, and combine the two Lyapunov drift inequalities through a cross-domination property. We believe this analytical framework is of independent interest and may be applicable to other coupled iterative algorithms with unbounded
Ishaq Hamza, Zaiwei Chen