• Python 2 or 3
• OpenAI Gym, version 0.11.0
• SciPy
• MatPlotLib

• Kernel Q-Learning with:

  • Continuous states / discrete actions
  • Continuous states and actions from ACC 2018

• Kernel Normalized Advantage Functions in continuous action spaces from IROS 2018

Kernel Q-Learning with Pendulum with prioritized experience replay

python rlcore.py cfg/kq_pendulum_per.cfg

Kernel NAF with Continuous Mountain Car

python rlcore.py cfg/knaf_mcar.cfg

Other options of configuration files are

• Kernel Q-Learning for Cont. Mountain Car: cfg/kq_cont_mcar.cfg
• Kernel Q-Learning for Pendulum: cfg/kq_pendulum.cfg
• Kernel Q-Learning for discrete-action Cartpole: cfg/kq_cartpole.cfg
• Kernel NAF for Pendulum: cfg/knaf_pendulum.cfg

The compose folder contains the code for composing two or more trained policies as described in the IROS 2018 paper.

To tune learning rates and other parameters, adjust the corresponding parameters in the .cfg file.

This software was created by Ekaterina Tolstaya, Ethan Stump, and Garrett Warnell.