Skip to content

MR.Q is a general-purpose model-free reinforcement learning algorithm.

License

Notifications You must be signed in to change notification settings

facebookresearch/MRQ

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MR.Q: Towards General-Purpose Model-Free Reinforcement Learning

PyTorch implementation of the MR.Q algorithm from Towards General-Purpose Model-Free Reinforcement Learning by Scott Fujimoto, Pierluca D'Oro, Amy Zhang, Yuandong Tian, and Michael Rabbat.

Installing

Experiments were originally run with Python 3.11, but Python 3.10-3.12 is supported.

git clone [email protected]:facebookresearch/MRQ.git
cd MRQ
pip install -r requirements.txt

Usage

Benchmark is designated by a prefix (Gym-, Dmc-, Dmc-visual-, Atari-) followed by the original environment name. A complete list of environments are contained in MRQ/utils.py.

Example usage:

cd MRQ
python main.py --env Gym-HalfCheetah-v4
python main.py --env Dmc-quadruped-walk
python main.py --env Dmc-visual-walker-walk
python main.py --env Atari-Pong-v5

Code Structure

Results

Results are formatted in human-readable .txt files under /results. There is a code snippet in MRQ/utils.py to process the .txt files into a dictionary of arrays.

License

MRQ is licensed under the CC BY-NC 4.0 license, as found in the LICENSE file.

About

MR.Q is a general-purpose model-free reinforcement learning algorithm.

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages