mlsanityData to 14 Oct 2026

ε-Policy Gradient for Online Pricing

arXiv 2405.03624 ↗First posted 6 May 2024cs.LG math.OC q-fin.STcited by 1

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

Combining model-based and model-free reinforcement learning approaches, this paper proposes and analyzes an ε-policy gradient algorithm for the online pricing learning task. The algorithm extends ε-greedy algorithm by replacing greedy exploitation with gradient descent step and facilitates learning via model inference. We optimize the regret of the proposed algorithm by quantifying the exploration cost in terms of the exploration probability ε and the exploitation cost in terms of the gradient descent optimization and gradient estimation errors. The algorithm achieves an expected regret of order O(√T) (up to a logarithmic factor) over T trials.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 24 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

14 of 24 references.

References · 14

  1. 2019Introduction to Online Convex Optimizationcited by 803
  2. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 539
  3. 2017On Kernelized Multi-armed Banditscited by 352
  4. 2020Loss landscapes and optimization in over-parameterized non-linear systems and neural networkscited by 233
  5. 2020On Information Gain and Regret Bounds in Gaussian Process Banditscited by 158
  6. 2020On the Convergence of SGD with Biased Gradientscited by 83
  7. 2019Adaptive Exploration in Linear Contextual Banditcited by 43
  8. 2020Logarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizoncited by 35
  9. 2021Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controlscited by 24
  10. 2021Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex modelscited by 21
  11. 2023Exploration via linearly perturbed loss minimisationcited by 13
  12. 2022Logarithmic regret bounds for continuous-time average-reward Markov decision processescited by 8
2 more
  1. 2022Square-root regret bounds for continuous-time episodic Markov decision processescited by 5
  2. 2021Generalised correlated batched bandits via the ARC algorithm with application to dynamic pricingcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Reinforcement Learning for Corporate Bond Trading: A Sell Side Perspectivecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Deep Reinforcement Learning for Online Optimal Execution Strategies
  2. 2022Stochastic Gradient Descent with Dependent Data for Offline Reinforcement Learning
  3. 2025Online Episodic Convex Reinforcement Learning
  4. 2021Fast Rates for the Regret of Offline Reinforcement Learning
  5. 2024A Tale of Two Cities: Pessimism and Opportunism in Offline Dynamic Pricing
  6. 2021Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
  7. 2025Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
  8. 2025Accelerated Portfolio Optimization and Option Pricing with Reinforcement Learning