Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.06514 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914375920517120 |
|---|---|
| author | Dagher, Esther Bou Perepelitsa, Misha Zatorska, Ewelina |
| author_facet | Dagher, Esther Bou Perepelitsa, Misha Zatorska, Ewelina |
| contents | We study a continuum model for stochastic reinforcement learning in repeated market entry games. Starting from a discrete-time microscopic learning rule, we derive a Fokker--Planck-type equation for the distribution of agents' propensities and, using a kinetic closure, obtain a nonlinear one-particle equation of a mean-field type. For the resulting Cauchy problem, we prove existence and uniqueness of solutions and analyze their long-time behavior. The PDE captures two key phenomena observed in market entry dynamics: aggregate learning (the average number of entrants approaches market capacity) and sorting (propensities concentrate near extreme behaviors). The model also yields explicit characteristic time scales, showing that aggregate learning occurs faster than sorting, in agreement with experimental and computational evidence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06514 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On a PDE model for Learning in Stochastic Market Entry Games Dagher, Esther Bou Perepelitsa, Misha Zatorska, Ewelina Analysis of PDEs We study a continuum model for stochastic reinforcement learning in repeated market entry games. Starting from a discrete-time microscopic learning rule, we derive a Fokker--Planck-type equation for the distribution of agents' propensities and, using a kinetic closure, obtain a nonlinear one-particle equation of a mean-field type. For the resulting Cauchy problem, we prove existence and uniqueness of solutions and analyze their long-time behavior. The PDE captures two key phenomena observed in market entry dynamics: aggregate learning (the average number of entrants approaches market capacity) and sorting (propensities concentrate near extreme behaviors). The model also yields explicit characteristic time scales, showing that aggregate learning occurs faster than sorting, in agreement with experimental and computational evidence. |
| title | On a PDE model for Learning in Stochastic Market Entry Games |
| topic | Analysis of PDEs |
| url | https://arxiv.org/abs/2603.06514 |