garage¶
garage is a toolkit for developing and evaluating reinforcement learning algorithms, and an accompanying library of state-of-the-art implementations built using that toolkit.
garage is a work in progress, input is welcome. The available documentation is limited, but rapidly growing.
User Guide¶
The garage user guide explains how to install garage, how to run experiments, and how to implement new MDPs and new algorithms.
- Run Experiments
- Use Image Observations
- Monitor Your Experiments with TensorBoard
- Train a Policy to Solve an Environment
- Save, Load and Resume Experiments
- Load and Use a Trained Policy
- Use a Pre-Trained Network to Start a New Experiment
- Run garage with Docker
- Ensure Your Experiments are Reproducible
- Run Meta-/Multi-Task RL Experiments
- Maximize Resource Usage
- Distribute Experiments Across Machines
Citing garage¶
If you use garage for academic research, please cite the repository using the
following BibTeX entry. You should update the commit
field with the commit or
release tag your publication uses.
@misc{garage,
author = {The garage contributors},
title = {Garage: A toolkit for reproducible reinforcement learning research},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/rlworkgroup/garage}},
commit = {ebd7800430b0212c3ffcf78fd3ec26b22097c371}