Published February 17, 2026
| Version v1.0.2
Software
Open
DynPricing PPO V8 Experiments
Authors/Creators
- 1. Instituto Metrópole Digital – Universidade Federal do Rio Grande do Norte (UFRN)
Description
Reproducible experimental framework for dynamic pricing in retail environments using Deep Reinforcement Learning (Proximal Policy Optimization – PPO) with temporal demand modeling. This repository contains the frozen V8 experimental configuration, including the MDP environment, training scripts, baseline evaluation, and final result artifacts.
Notes
If you use this experimental framework in your research, please cite it as follows.
Files
wagnervlopes/dynpricing-ppo-v8-experiments-v1.0.2.zip
Files
(4.4 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:bad408e849f26bda98040d6d4f1aefb0
|
4.4 kB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/wagnervlopes/dynpricing-ppo-v8-experiments/tree/v1.0.2 (URL)