Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (16.1%) to scientific vocabulary
Keywords
Repository
Reinforcement learning library in JAX.
Basic Info
Statistics
- Stars: 100
- Watchers: 9
- Forks: 3
- Open Issues: 0
- Releases: 0
Topics
Metadata Files
README.md
Magi RL library in JAX
Installation | Agents | Examples | Contributing | Documentation
Note Future development of JAX agents in Magi have moved to Corax
Magi is a RL library in JAX that is fully compatible with Acme.
In addition to the features provided by Acme, Magi offers implementation of RL agents that are not found in the Acme repository as well as providing useful tools for integrating experiment logging services such as WandB.
Note: Magi is in alpha development so expect breaking changes!
Magi currently depends on HEAD version of dm-acme instead of the latest release version on PyPI which is fairly old.
Installation
Create a new Python virtual environment
bash python3 -m venv venv source venv/bin/activateInstall dependencies with the following commands.
```bash pip install -U pip setuptools wheel
Magi depends on latest version of dm-acme.
The dependencies in setup.py are abstract which allows you to pin
a specific version of dm-acme.
The following command installs the latest version of dm-acme
pip install 'git+https://github.com/deepmind/acme.git#egg=dm-acme[jax,tf,examples]'
Install magi in editable mode, with additional dependencies.
In case you need to run examples on GPU, you should install the
GPU version of JAX with a command like the following
pip install 'jax[cuda]<0.4' -f https://storage.googleapis.com/jax-releases/jaxcudareleases.html pip install -e '.[jax]' ```
The base installation for magi does not list TensorFlow/JAX as a dependency. However, note that JAX requires platform-specific installation (CPU/GPU and CUDA versions). Furthermore, Acme depends on Reverb and LaunchPad which requires them to be pinned against specific versions of TensorFlow. This should be handled if you use install dm-acme with [jax,tf] extras. However, you can also use install with different versions of TensorFlow/Reverb/Launchpad. In that case, you should omit the extras and find compatible versions and pin those versions accordingly.
If for some reason installation fails, first check out GitHub Actions badge to see if this fails on the latest CI run. If the CI is successful, then it's likely that there are some issues to setting up your own environment. Refer to .github/workflows/ci.yaml as the official source for how to set up the environment.
Agents
magi includes popular RL algorithm implementation such as SAC, DrQ, SAC-AE and PETS. Refer to magi/agents for a full list of agents.
Examples
Check out examples where we include examples of using our RL agents on popular benchmark tasks.
Testing
On Linux, you can run tests with
nox test
Contributing
Refer to CONTRIBUTING.md.
Acknowledgements
Magi is inspired by many of the open-source RL projects out there. Here is a (non-exhaustive) list of related libraries and packages that Magi references:
- https://github.com/deepmind/acme
- https://github.com/ikostrikov/jaxrl
- https://github.com/tensorflow/agents
- https://github.com/rail-berkeley/rlkit
License
Citation
If you use Magi in your work, please cite us according to the CITATION file. You may learn more about the CITATION file from here.
Owner
- Name: Yicheng Luo
- Login: ethanluoyc
- Kind: user
- Location: London, United Kingdom
- Company: University College London
- Website: luoyicheng.net
- Twitter: LuoYicheng
- Repositories: 145
- Profile: https://github.com/ethanluoyc
PhD student at UCL AI Center. Former intern at @deepmind and @secondmind-labs.
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - family-names: "Luo" given-names: "Yicheng" orcid: "https://orcid.org/0000-0003-0547-411X" title: "Magi: Research Reinforcement Learning Library in JAX" version: 0.0.1 date-released: 2021-11-07 url: "https://github.com/ethanluoyc/magi"
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1
Dependencies
- mujoco-py ==1.50.1.1
- gym >=0.21.0
- mujoco_py >=1.50,<2.0
- wandb *
- PyYAML *
- absl-py *
- chex *
- dm-acme *
- dm-haiku *
- dm-launchpad *
- dm-reverb *
- dm-tree *
- gym *
- jax ==0.3.6
- ml_collections *
- numpy *
- optax *
- rlax *
- tensorflow ==2.8.0
- tensorflow_probability ==0.15.0
- wandb *
- 104 dependencies
- isort *
- nox *
- pip-compile-multi *
- pre-commit *
- pylint *
- pytype *
- yapf *
- argcomplete ==1.12.3
- astroid ==2.11.6
- cfgv ==3.3.1
- colorlog ==6.6.0
- distlib ==0.3.4
- filelock ==3.7.1
- identify ==2.5.1
- importlab ==0.7
- isort ==5.10.1
- lazy-object-proxy ==1.7.1
- libcst ==0.4.5
- mccabe ==0.7.0
- mypy-extensions ==0.4.3
- networkx ==2.8.3
- ninja ==1.10.2.3
- nodeenv ==1.6.0
- nox ==2022.1.7
- pep517 ==0.12.0
- pip-compile-multi ==2.4.5
- pip-tools ==6.6.2
- platformdirs ==2.5.2
- pre-commit ==2.19.0
- pydot ==1.4.2
- pylint ==2.14.2
- pytype ==2022.6.14
- toml ==0.10.2
- tomlkit ==0.11.0
- toposort ==1.7
- typing-inspect ==0.7.1
- virtualenv ==20.14.1
- yapf ==0.32.0
- pytest *
- pytest-xdist *
- execnet ==1.9.0
- iniconfig ==1.1.1
- pluggy ==1.0.0
- py ==1.11.0
- pytest ==7.1.2
- pytest-forked ==1.4.0
- pytest-xdist ==2.5.0
- tomli ==2.0.1
- DeepMind *
- JAX *
- Tensorflow *
- absl-py *
- chex *
- dm-acme *
- dm-haiku *
- dm-launchpad *
- dm-reverb *
- jax *
- numpy *
- optax *
- rlax *
- tensorflow *
- tensorflow_probability *