d-tiapkin / rand-ql

Repository for a paper "Model-free Posterior Sampling via Learning Rate Randomization"

Model-free Posterior Sampling via Learning Rate Randomization

To run the tabular experiment on GridWorld environment:

    python run.py config/experimets/randql_vs_baseline.yaml

To make plots:

    python plot_randql_vs_baseline.py

Requirements:

• Python 3.8
• rlberry 0.4.0