StatisticalReinforcementLearningLab/oralytics_reward_design

Code for "Reward Design For An Online Reinforcement Learning Algorithm For Supporting Oral Self-Care” Paper

Code for "Reward Design For An Online Reinforcement Learning Algorithm For Supporting Oral Self-Care”

---

Organization

The package is organized in the following way:

Simulation Environment

• Fitting parameters for the simualtion environment base model: fitting_simulation_base_model.py
• Forming the prior for the RL algorithm: forming_prior_using_robas_2.py
• Simulation Envrionment Code: simulation_environment.py

RL Algorithm

• RL Algorithm Code: rl_algorithm.py

Experiments

• Main Experiment Function: rl_experiments.py
• Code for parallelization and calling experiment function: run_rl_experiment.py

Metrics and Figures

• Computing metrics and plotting figures: metric_computations.py and plot_figures.py