Fast Convergence of Policy Regret in Learning Stochastic Optimal Control

• URL: http://arxiv.org/abs/2605.26361v1
• Date: Mon, 25 May 2026 22:07:24 GMT
• Title: Fast Convergence of Policy Regret in Learning Stochastic Optimal Control
• Abstract summary: We study policy learning in optimal control, a greedy policy induced by an estimate of the optimal action-value function $Q*$.<n>We show that, in continuous action spaces, fast policy learning is induced by three geometric structures: a growth exponent $p$, a margin-mass exponent $m$, and an action-wise regularity exponent $q$.
• Score: 7.896895563709477
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Policy learning in modern operations environments faces a fundamental tension between limited operational data and the large, often continuous, state and action spaces over which good decisions must be identified and deployed. We study value-based policy learning in stochastic optimal control: a greedy policy induced by an estimate of the optimal action-value function $Q^*$ is deployed, and its performance is measured by regret. The empirical success of this approach calls for statistical insight into the structures that enable fast regret convergence. We show that, in continuous action spaces, fast policy learning is induced by three geometric structures: a growth exponent $p$, which quantifies how quickly $Q^*$ separates suboptimal actions from its maximizers; a margin-mass exponent $m$, which controls how much deployment mass lies on states with weak growth; and an action-wise regularity exponent $q$, which measures the smoothness of the $Q^*$-estimation error across actions. Given a $n^{-1/2}$-accurate estimator of $Q^*$, we show that the minimax-optimal policy regret convergence rate is \[ \widetildeΘ\left( n^{-\min\left\{\frac{p}{2(p-q)},\frac{m+1}{2m}\right\}} \right), \] up to a logarithmic factor at the boundary between the two regimes. The exponent $q$ is crucial: $q>0$ yields faster-than-$n^{-1/2}$ regret. This regime is natural in operations applications. In particular, we verify $q>0$ under mild regularity conditions in dynamic inventory control and service allocation examples, while the mechanism underlying this fast rate regime extends beyond these settings.

Related papers

• Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space [0.0]
  We revisit the regret of undiscounted reinforcement learning in MDPs with a birth and death structure. In our main result, we show that the regret of a slightly-ted version of the classical learning algorithm sc Ucrl2 is in fact upper bounded by $tildemathcalO(sqrtEAT)$ where $E$ is related to the weighted second moment of the stationary measure of a reference policy.
  arXiv  Detail & Related papers  (2023-02-21T13:28:37Z)
• Autoregressive Bandits [58.46584210388307]
  We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
  arXiv  Detail & Related papers  (2022-12-12T21:37:36Z)
• Minimal Expected Regret in Linear Quadratic Control [79.81807680370677]
  We devise an online learning algorithm and provide guarantees on its expected regret. This regret at time $T$ is upper bounded (i) by $widetildeO((d_u+d_x)sqrtd_xT)$ when $A$ and $B$ are unknown.
  arXiv  Detail & Related papers  (2021-09-29T14:07:21Z)
• Implicitly Regularized RL with Implicit Q-Values [42.87920755961722]
  The $Q$-function is a central quantity in many Reinforcement Learning (RL) algorithms for which RL agents behave following a (soft)-greedy policy. We propose to parametrize the $Q$-function implicitly, as the sum of a log-policy and of a value function. We derive a practical off-policy deep RL algorithm, suitable for large action spaces, and that enforces the softmax relation between the policy and the $Q$-value.
  arXiv  Detail & Related papers  (2021-08-16T12:20:47Z)
• Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret [144.6358229217845]
  We study the problem of learning in the shortest path (SSP) setting, where an agent seeks to minimize the expected cost accumulated before reaching a goal state. We design a novel model-based algorithm EB-SSP that carefully skews the empirical transitions and perturbs the empirical costs with an exploration bonus. We prove that EB-SSP achieves the minimax regret rate $widetildeO(B_star sqrtS A K)$, where $K$ is the number of episodes, $S$ is the number of states, $A$
  arXiv  Detail & Related papers  (2021-04-22T17:20:48Z)
• Softmax Policy Gradient Methods Can Take Exponential Time to Converge [60.98700344526674]
  The softmax policy gradient (PG) method is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. We demonstrate that softmax PG methods can take exponential time -- in terms of $mathcalS|$ and $frac11-gamma$ -- to converge.
  arXiv  Detail & Related papers  (2021-02-22T18:56:26Z)
• Fast Rates for the Regret of Offline Reinforcement Learning [69.23654172273085]
  We study the regret of reinforcement learning from offline data generated by a fixed behavior policy in an infinitehorizon discounted decision process (MDP) We show that given any estimate for the optimal quality function $Q*$, the regret of the policy it defines converges at a rate given by the exponentiation of the $Q*$-estimate's pointwise convergence rate.
  arXiv  Detail & Related papers  (2021-01-31T16:17:56Z)
• Finite Continuum-Armed Bandits [0.0]
  We consider a situation where an agent has $T$ ressources to be allocated to a larger number of actions. The goal of the agent is to maximize her cumulative reward.
  arXiv  Detail & Related papers  (2020-10-23T08:48:45Z)
• Provably Efficient Safe Exploration via Primal-Dual Policy Optimization [105.7510838453122]
  We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation. We present an provably efficient online policy optimization algorithm for CMDP with safe exploration in the function approximation setting.
  arXiv  Detail & Related papers  (2020-03-01T17:47:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.