https://github.com/google/dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Committers with academic emails
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (13.2%) to scientific vocabulary

Keywords

ai google ml rl tensorflow

Keywords from Contributors

research reinforcement-learning deep-neural-networks distributed tpu jax

Last synced: 5 months ago · JSON representation

Repository

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Basic Info

Host: GitHub
Owner: google
License: apache-2.0
Language: Jupyter Notebook
Default Branch: master
Homepage: https://github.com/google/dopamine
Size: 26.7 MB

Statistics

Stars: 10,799
Watchers: 417
Forks: 1,390
Open Issues: 110
Releases: 2

Topics

ai google ml rl tensorflow

Created over 7 years ago · Last pushed over 1 year ago

Metadata Files

Readme Contributing License Authors

Dopamine

Getting Started | Docs | Baseline Results | Changelist

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms. It aims to fill the need for a small, easily grokked codebase in which users can freely experiment with wild ideas (speculative research).

Our design principles are:

Easy experimentation: Make it easy for new users to run benchmark experiments.
Flexible development: Make it easy for new users to try out research ideas.
Compact and reliable: Provide implementations for a few, battle-tested algorithms.
Reproducible: Facilitate reproducibility in results. In particular, our setup follows the recommendations given by Machado et al. (2018).

Dopamine supports the following agents, implemented with jax:

For more information on the available agents, see the docs.

Many of these agents also have a tensorflow (legacy) implementation, though newly added agents are likely to be jax-only.

This is not an official Google product.

Getting Started

We provide docker containers for using Dopamine. Instructions can be found here.

Alternatively, Dopamine can be installed from source (preferred) or installed with pip. For either of these methods, continue reading at prerequisites.

Prerequisites

Dopamine supports Atari environments and Mujoco environments. Install the environments you intend to use before you install Dopamine:

Atari

These should now come packaged with ale_py.
You may need to manually run some steps to properly install baselines, see instructions.

Mujoco

Install Mujoco and get a license here.
Run pip install mujoco-py (we recommend using a virtual environment).

Installing from Source

The most common way to use Dopamine is to install it from source and modify the source code directly:

git clone https://github.com/google/dopamine

After cloning, install dependencies:

pip install -r dopamine/requirements.txt

Dopamine supports tensorflow (legacy) and jax (actively maintained) agents. View the Tensorflow documentation for more information on installing tensorflow.

Note: We recommend using a virtual environment when working with Dopamine.

Installing with Pip

Note: We strongly recommend installing from source for most users.

Installing with pip is simple, but Dopamine is designed to be modified directly. We recommend installing from source for writing your own experiments.

pip install dopamine-rl

Running tests

You can test whether the installation was successful by running the following from the dopamine root directory.

export PYTHONPATH=$PYTHONPATH:$PWD python -m tests.dopamine.atari_init_test

Next Steps

View the docs for more information on training agents.

We supply baselines for each Dopamine agent.

We also provide a set of Colaboratory notebooks which demonstrate how to use Dopamine.

References

Bellemare et al., The Arcade Learning Environment: An evaluation platform for general agents. Journal of Artificial Intelligence Research, 2013.

Machado et al., Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents, Journal of Artificial Intelligence Research, 2018.

Hessel et al., Rainbow: Combining Improvements in Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2018.

Mnih et al., Human-level Control through Deep Reinforcement Learning. Nature, 2015.

Schaul et al., Prioritized Experience Replay. Proceedings of the International Conference on Learning Representations, 2016.

Haarnoja et al., Soft Actor-Critic Algorithms and Applications, arXiv preprint arXiv:1812.05905, 2018.

Schulman et al., Proximal Policy Optimization Algorithms.

Giving credit

If you use Dopamine in your work, we ask that you cite our white paper. Here is an example BibTeX entry:

@article{castro18dopamine, author = {Pablo Samuel Castro and Subhodeep Moitra and Carles Gelada and Saurabh Kumar and Marc G. Bellemare}, title = {Dopamine: {A} {R}esearch {F}ramework for {D}eep {R}einforcement {L}earning}, year = {2018}, url = {http://arxiv.org/abs/1812.06110}, archivePrefix = {arXiv} }

Owner

Name: Google
Login: google
Kind: organization
Email: opensource@google.com
Location: United States of America

Website: https://opensource.google/
Twitter: GoogleOSS
Repositories: 2,773
Profile: https://github.com/google

Google ❤️ Open Source

GitHub Events

Total

Issues event: 7
Watch event: 275
Issue comment event: 13
Push event: 5
Pull request review event: 1
Pull request event: 2
Fork event: 33

Last Year

Issues event: 7
Watch event: 275
Issue comment event: 13
Push event: 5
Pull request review event: 1
Pull request event: 2
Fork event: 33

Committers

Last synced: 6 months ago

All Time

Total Commits: 346
Total Committers: 16
Avg Commits per committer: 21.625
Development Distribution Score (DDS): 0.555

Past Year

Commits: 6
Committers: 2
Avg Commits per committer: 3.0
Development Distribution Score (DDS): 0.167

Top Committers

Name	Email	Commits
Pablo Samuel Castro	p**c@g**m	154
Dopamine Team	n**y@g**m	53
Alexandre Vassalotti	a**i@g**m	49
Rishabh Agarwal	r**l@g**m	26
Joshua Greaves	j**s@g**m	24
Utku Evci	e**u@g**m	9
Marc G. Bellemare	b**e@g**m	8
Johan Obando Ceron	o**n@g**m	7
Subhodeep Moitra	s**a@g**m	5
Baruch Tabanpour	b**a@g**m	3
Jing Conan Wang	j**g@g**m	2
Ted Willke	t**e@i**m	2
Chih-wei Hsu	c**u@g**m	1
Marlos C. Machado	m**m@g**m	1
Olivier Teboul	o**t@g**m	1
William Fedus	l**s@g**m	1

Committer Domains (Top 20 + Academic)

google.com: 15 intel.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 92
Total pull requests: 32
Average time to close issues: 3 months
Average time to close pull requests: 6 months
Total issue authors: 71
Total pull request authors: 27
Average comments per issue: 2.87
Average comments per pull request: 1.63
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 3

Past Year

Issues: 9
Pull requests: 1
Average time to close issues: 4 days
Average time to close pull requests: 6 minutes
Issue authors: 8
Pull request authors: 1
Average comments per issue: 0.89
Average comments per pull request: 3.0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

RylanSchaeffer (5)
GoingMyWay (4)
rfali (3)
sunchipsster1 (3)
FelipeMartins96 (3)
theovincent (2)
ZifanWu (2)
bryanyuan1 (2)
satst27 (2)
amrzv (2)
xinghua-qu (2)
pseudo-rnd-thoughts (2)
sunhao12121 (2)
phoenixjyb (1)
tylerkastner (1)

Pull Request Authors

dependabot[bot] (3)
modanesh (3)
mingless (2)
Yaskm08 (2)
erick-hash (2)
joaogui1 (1)
athulkannan2000 (1)
JesseFarebro (1)
SwanseaLeo (1)
MaxASchwarzer (1)
ddlau (1)
mklissa (1)
Mattia-Colbertaldo (1)
crobarcro (1)
jjh42 (1)

Top Labels

Issue Labels

Pull Request Labels

cla: yes (19) dependencies (3) cla: no (2)

Packages

Total packages: 1
Total downloads:
- pypi 25,565 last-month
Total docker downloads: 24,427,969

Total dependent packages: 4
Total dependent repositories: 733
Total versions: 38
Total maintainers: 1

pypi.org: dopamine-rl

Dopamine: A framework for flexible Reinforcement Learning research

Homepage: https://github.com/google/dopamine
Documentation: https://github.com/google/dopamine
License: Apache 2.0
Latest release: 4.1.2
published over 1 year ago

Versions: 38
Dependent Packages: 4
Dependent Repositories: 733
Downloads: 25,565 Last month
Docker Downloads: 24,427,969

Rankings

Stargazers count: 0.2%

Dependent repos count: 0.4%

Docker downloads count: 0.7%

Average: 1.1%

Forks count: 1.1%

Downloads: 1.6%

Dependent packages count: 2.4%

Maintainers (1)

dopamine

Last synced: 6 months ago

Dependencies

dopamine/labs/tandem_dqn/requirements.txt pypi

absl-py *
atari-py *
dopamine-rl *
gin-config *
gym *
numpy *
tensorflow *

requirements.txt pypi

Keras-Preprocessing >=1.1.2
Markdown >=3.2.2
Pillow >=7.2.0
Werkzeug >=1.0.1
absl-py >=0.9.0
astunparse >=1.6.3
atari-py >=0.2.6
cachetools >=4.1.1
certifi >=2020.6.20
chardet >=3.0.4
cloudpickle >=1.3.0
cycler >=0.10.0
flax >=0.3.3
future >=0.18.2
gast >=0.3.3
gin-config >=0.3.0
google-auth >=1.19.2
google-auth-oauthlib >=0.4.1
google-pasta >=0.2.0
grpcio >=1.30.0
gym >=0.17.2
h5py >=2.10.0
idna >=2.10
jax >=0.2.12
jaxlib >=0.1.65
kiwisolver >=1.2.0
matplotlib >=3.3.0
msgpack >=1.0.0
numpy >=1.18.5
oauthlib >=3.1.0
opencv-python >=4.3.0.36
opt-einsum >=3.3.0
pandas >=1.0.5
protobuf >=3.12.2
pyasn1 >=0.4.8
pyasn1-modules >=0.2.8
pygame >=1.9.6
pyglet >=1.5.0
pyparsing >=2.4.7
python-dateutil >=2.8.1
pytz >=2020.1
requests >=2.24.0
requests-oauthlib >=1.3.0
rsa >=4.6
scipy >=1.4.1
setuptools >=49.2.01
six >=1.15.0
tensorboard *
tensorboard-plugin-wit *
tensorflow *
tensorflow-estimator *
tensorflow-probability >=0.13.0
termcolor >=1.1.0
tf-slim >=1.1.0
urllib3 >=1.25.10
wrapt >=1.12.1

setup.py pypi

absl-py *
gin-config *
gym *
opencv-python *
tensorflow *

docker/atari/Dockerfile docker

${base_image} latest build

docker/core/Dockerfile docker

nvidia/cuda ${cuda_docker_tag} build

docker/mujoco/Dockerfile docker

${base_image} latest build

https://github.com/google/dopamine

Science Score: 23.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

Dopamine

Getting Started

Prerequisites

Installing from Source

Installing with Pip

Running tests

Next Steps

References

Giving credit

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: dopamine-rl

Rankings

Maintainers (1)

Dependencies