$$\epsilon $$-Policy Gradient for Online Pricing
Abstract
Abstract Combining model-based and model-free reinforcement learning approaches, this paper proposes and analyzes an $$\epsilon $$ ϵ -policy gradient algorithm for the online pricing learning task. The algorithm extends $$\epsilon $$ 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 $$\epsilon $$ ϵ and the exploitation cost in terms of the gradient descent optimization and gradient estimation errors. The algorithm achieves an expected regret of order $$\mathcal {O}(\sqrt{T})$$ O ( T ) (up to a logarithmic factor) over T trials.
Fields of Study & Subjects
Auction Theory and Applications
Consumer Market Behavior and Pricing
Advanced Bandit Algorithms Research
Publication details
- Journal / source
- Applied Mathematics & Optimization
- Publisher
- Springer Science and Business Media LLC
- Volume
- 94
- Issue
- 1
- Publication date
- 2 July 2026
- Language
- EN