This repository contains the source code for the numerical experiments presented in the paper On the Unreasonable Efficiency of State Space Clustering in Personalization Tasks.
- Install the requirements via
pip install -r requirements.txt
- Configure the environment in
config.yaml
- Run the experiments via
python -m run_experiments
synthetic_gaussian_mapping.py
--- creates the Synthetic Gaussian Mapping that acts as a latent feature extractor for the simulated reward signalbandit_environment.py
--- creates the Synthetic Hyperpersonalization Environment with the simulated reward signal as an OpenAI Gym environmentonline_rl.py
--- trains online RL algorithms on a given environmentrun_experiments.py
--- sets up and runs the experimentsconfig.yaml
--- stores the environment/training/experiment parametersrequirements.txt
--- lists the required packages
This project is licensed under the MIT License.