Paper available here.

The algorithm is implemented in the folder algorithms/. The folder config/ contains the parameters defining the experiments.

• Requirements:

  • Python 3.7
  • rlberry version 0.1
  • pyyaml

• Create and activate conda virtual environment (optional)

$ conda create -n rl_fast_active_learning_env python=3.7
$ conda activate rl_fast_active_learning_env

• Install requirements

$ pip install 'rlberry[full]==0.1'
$ pip install pyyaml

• Run and plot

$ python run.py config/experiment.yaml --n_fit=4
$ python plot.py