Science Score: 20.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org, nature.com -
✓Committers with academic emails
3 of 41 committers (7.3%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.4%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
Deep Reinforcement Learning for Keras.
Basic Info
- Host: GitHub
- Owner: keras-rl
- License: mit
- Language: Python
- Default Branch: master
- Homepage: http://keras-rl.readthedocs.io/
- Size: 1.35 MB
Statistics
- Stars: 5,556
- Watchers: 198
- Forks: 1,356
- Open Issues: 49
- Releases: 8
Topics
Metadata Files
README.md
Deep Reinforcement Learning for Keras
 |
 |
 |
What is it?
keras-rl implements some state-of-the art deep reinforcement learning algorithms in Python and seamlessly integrates with the deep learning library Keras.
Furthermore, keras-rl works with OpenAI Gym out of the box. This means that evaluating and playing around with different algorithms is easy.
Of course you can extend keras-rl according to your own needs. You can use built-in Keras callbacks and metrics or define your own.
Even more so, it is easy to implement your own environments and even algorithms by simply extending some simple abstract classes. Documentation is available online.
What is included?
As of today, the following algorithms have been implemented:
- [x] Deep Q Learning (DQN) [1], [2]
- [x] Double DQN [3]
- [x] Deep Deterministic Policy Gradient (DDPG) [4]
- [x] Continuous DQN (CDQN or NAF) [6]
- [x] Cross-Entropy Method (CEM) [7], [8]
- [x] Dueling network DQN (Dueling DQN) [9]
- [x] Deep SARSA [10]
- [ ] Asynchronous Advantage Actor-Critic (A3C) [5]
- [ ] Proximal Policy Optimization Algorithms (PPO) [11]
You can find more information on each agent in the doc.
Installation
- Install Keras-RL from Pypi (recommended):
pip install keras-rl
- Install from Github source:
git clone https://github.com/keras-rl/keras-rl.git
cd keras-rl
python setup.py install
Examples
If you want to run the examples, you'll also have to install:
- gym by OpenAI: Installation instruction
- h5py: simply run
pip install h5py
For atari example you will also need:
- Pillow:
pip install Pillow - gym[atari]: Atari module for gym. Use
pip install gym[atari]
Once you have installed everything, you can try out a simple example:
bash
python examples/dqn_cartpole.py
This is a very simple example and it should converge relatively quickly, so it's a great way to get started! It also visualizes the game during training, so you can watch it learn. How cool is that?
Some sample weights are available on keras-rl-weights.
If you have questions or problems, please file an issue or, even better, fix the problem yourself and submit a pull request!
External Projects
You're using Keras-RL on a project? Open a PR and share it!
Visualizing Training Metrics
To see graphs of your training progress and compare across runs, run pip install wandb and add the WandbLogger callback to your agent's fit() call:
```python from rl.callbacks import WandbLogger
...
agent.fit(env, nb_steps=50000, callbacks=[WandbLogger()]) ```
For more info and options, see the W&B docs.
Citing
If you use keras-rl in your research, you can cite it as follows:
bibtex
@misc{plappert2016kerasrl,
author = {Matthias Plappert},
title = {keras-rl},
year = {2016},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/keras-rl/keras-rl}},
}
References
- Playing Atari with Deep Reinforcement Learning, Mnih et al., 2013
- Human-level control through deep reinforcement learning, Mnih et al., 2015
- Deep Reinforcement Learning with Double Q-learning, van Hasselt et al., 2015
- Continuous control with deep reinforcement learning, Lillicrap et al., 2015
- Asynchronous Methods for Deep Reinforcement Learning, Mnih et al., 2016
- Continuous Deep Q-Learning with Model-based Acceleration, Gu et al., 2016
- Learning Tetris Using the Noisy Cross-Entropy Method, Szita et al., 2006
- Deep Reinforcement Learning (MLSS lecture notes), Schulman, 2016
- Dueling Network Architectures for Deep Reinforcement Learning, Wang et al., 2016
- Reinforcement learning: An introduction, Sutton and Barto, 2011
- Proximal Policy Optimization Algorithms, Schulman et al., 2017
Owner
- Name: Keras-RL
- Login: keras-rl
- Kind: organization
- Website: https://keras-rl.readthedocs.io/en/latest/
- Repositories: 1
- Profile: https://github.com/keras-rl
GitHub Events
Total
- Watch event: 67
- Issue comment event: 1
- Fork event: 4
Last Year
- Watch event: 67
- Issue comment event: 1
- Fork event: 4
Committers
Last synced: about 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| Matthias Plappert | m****t@m****m | 176 |
| Raphael | r****c@g****m | 24 |
| luffy | r****8@g****m | 13 |
| Ryan Hope | r****3@g****m | 5 |
| junfeng rao | r****u@q****m | 4 |
| Jonathan Rahn | r****n@g****m | 3 |
| yujia21 | o****t@g****m | 2 |
| showay | d****2@g****m | 2 |
| obsproth | o****h | 2 |
| Vrishank Bhardwaj | v****7@g****m | 2 |
| SimonRamstedt | s****t@g****m | 2 |
| Olivier Delalleau | d****a | 2 |
| Evan Hubinger | e****b@g****m | 2 |
| Dr. Kashif Rasul | k****l@g****m | 2 |
| Ben | b****r | 2 |
| Ali Kheyrollahi | a****b@g****m | 2 |
| Matthias Plappert | m****s@o****m | 2 |
| jmo-gs | j****o@g****c | 1 |
| John Qian | j****n@l****g | 1 |
| Olivier Delalleau | o****u@u****m | 1 |
| Partha Ghosh | p****h@s****h | 1 |
| Susannah Klaneček | sk@n****o | 1 |
| bkj | b****n@g****m | 1 |
| Abhinav | a****6@v****n | 1 |
| bjmuld | b****d | 1 |
| arthur-hav | a****k@g****m | 1 |
| Unknown | d****s@h****m | 1 |
| Petri Partanen | p****n | 1 |
| Nico | N****d | 1 |
| Neves4 | v****8@g****m | 1 |
| and 11 more... | ||
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 12 months ago
All Time
- Total issues: 86
- Total pull requests: 22
- Average time to close issues: 6 months
- Average time to close pull requests: 12 months
- Total issue authors: 81
- Total pull request authors: 20
- Average comments per issue: 3.3
- Average comments per pull request: 0.59
- Merged pull requests: 2
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 2
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 2
- Pull request authors: 0
- Average comments per issue: 0.5
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- jarlva (2)
- STRATZ-Ken (2)
- loveyandex (2)
- palbha (2)
- Saber-xxf (2)
- mdavis-xyz (1)
- tensorneko (1)
- jxiw (1)
- Cpt-Falcon (1)
- gioiav (1)
- harleyxu-xhl (1)
- sandra-sys (1)
- shravansuthar210 (1)
- imandr (1)
- toksis (1)
Pull Request Authors
- danielduffield (2)
- lbosk (2)
- shijianjian (1)
- kaixinbaba (1)
- testytestytestytest (1)
- stefanbschneider (1)
- jayaneetha (1)
- Xyzrr (1)
- LyWangPX (1)
- VinQbator (1)
- msat59 (1)
- dmckinno (1)
- Nikolay-Lysenko (1)
- yujia21 (1)
- hamzamerzic (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 2
-
Total downloads:
- pypi 683 last-month
- Total docker downloads: 17,431
-
Total dependent packages: 0
(may contain duplicates) -
Total dependent repositories: 164
(may contain duplicates) - Total versions: 15
- Total maintainers: 2
pypi.org: keras-rl
Deep Reinforcement Learning for Keras
- Homepage: https://github.com/keras-rl/keras-rl
- Documentation: https://keras-rl.readthedocs.io/
- License: MIT
-
Latest release: 0.4.2
published about 8 years ago
Rankings
Maintainers (2)
proxy.golang.org: github.com/keras-rl/keras-rl
- Documentation: https://pkg.go.dev/github.com/keras-rl/keras-rl#section-documentation
- License: mit
-
Latest release: v0.4.2
published about 8 years ago
Rankings
Dependencies
- mkdocs *
- numpy *
- python-markdown-math *
- keras >=2.0.7