معرفی شرکت ها
baconian-0.2.6
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشترتوضیحات
model-based reinforcement learning toolbox
| ویژگی | مقدار |
|---|---|
| سیستم عامل | - |
| نام فایل | baconian-0.2.6 |
| نام | baconian |
| نسخه کتابخانه | 0.2.6 |
| نگهدارنده | [] |
| ایمیل نگهدارنده | [] |
| نویسنده | Linsen Dong |
| ایمیل نویسنده | linsen001@e.ntu.edu.sg |
| آدرس صفحه اصلی | https://github.com/cap-ntu/baconian-project |
| آدرس اینترنتی | https://pypi.org/project/baconian/ |
| مجوز | MIT License |
# Baconian: Boosting model-based reinforcement learning
[](https://travis-ci.com/cap-ntu/baconian-project)
[](https://baconian-public.readthedocs.io/en/latest/?badge=latest)
[](https://www.codacy.com/app/Lukeeeeee/baconian?utm_source=github.com&utm_medium=referral&utm_content=Lukeeeeee/baconian&utm_campaign=Badge_Grade)
[](https://codecov.io/gh/Lukeeeeee/baconian-project)
Baconian [beˈkonin] is a toolbox for model-based reinforcement learning with user-friendly experiment setting-up, logging
and visualization modules developed by [CAP](http://cap.scse.ntu.edu.sg/). We aim to develop a flexible, re-usable and
modularized framework that can allow the users to easily set-up their model-based RL experiments by reusing modules we
provide.
### Installation
You can easily install by (with python 3.5/3.6/3.7, Ubuntu 16.04/18.04):
```bash
# install tensorflow with/without GPU based on your machine
pip install tensorflow-gpu==1.15.2
# or
pip install tensorflow==1.15.2
pip install baconian
```
For more advance usage like using Mujoco environment, please refer to our documentation page.
### Release news:
- 2020.04.29 v0.2.2 Fix some memory issues in SampleData module, and simplify some APIs.
- 2020.02.10 We are including external reward & terminal function of Gym/mujoco tasks with well-written documents.
- 2020.01.30 Update some dependent packages versions, and release some preliminary benchmark results with hyper-parameters.
For previous news, please go [here](./old_news.md)
### Documentation
We support python 3.5, 3.6, and 3.7 with Ubuntu 16.04 or 18.04.
Documentation is available at http://baconian-public.readthedocs.io/
### Algorithms Reference:
#### Model-based:
#### 1. Dyna
Sutton, Richard S. "Dyna, an integrated architecture for learning, planning, and reacting." ACM Sigart Bulletin 2.4 (1991): 160-163.
#### 2. LQR
Abbeel, P. "Optimal Control for Linear Dynamical Systems and Quadratic Cost (‘LQR’)." (2012).
#### 3. iLQR
Abbeel, P. "Optimal Control for Linear Dynamical Systems and Quadratic Cost (‘LQR’)." (2012).
#### 4. MPC
Garcia, Carlos E., David M. Prett, and Manfred Morari. "Model predictive control: theory and practice—a survey." Automatica 25.3 (1989): 335-348.
#### 5. Model-ensemble
Kurutach, Thanard, et al. "Model-ensemble trust-region policy optimization." arXiv preprint arXiv:1802.10592 (2018).
#### Model-free
#### 1. DQN
Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning." arXiv preprint arXiv:1312.5602 (2013).
#### 2. PPO
Schulman, John, et al. "Proximal policy optimization algorithms." arXiv preprint arXiv:1707.06347 (2017).
#### 3. DDPG
Lillicrap, Timothy P., et al. "Continuous control with deep reinforcement learning." arXiv preprint arXiv:1509.02971 (2015).
### Algorithms in Progress
#### 1. Random Shooting
Rao, Anil V. "A survey of numerical methods for optimal control." Advances in the Astronautical Sciences 135.1 (2009): 497-528.
#### 2. MB-MF
Nagabandi, Anusha, et al. "Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning." 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2018.
#### 3. GPS
Levine, Sergey, et al. "End-to-end training of deep visuomotor policies." The Journal of Machine Learning Research 17.1 (2016): 1334-1373.
### Acknowledgement
Thanks to the following open-source projects:
- garage: https://github.com/rlworkgroup/garage
- rllab: https://github.com/rll/rllab
- baselines: https://github.com/openai/baselines
- gym: https://github.com/openai/gym
- trpo: https://github.com/pat-coady/trpo
### Citing Baconian
If you find Baconian is useful for your research, please consider cite our demo paper here:
```
@article{
linsen2019baconian,
title={Baconian: A Unified Opensource Framework for Model-Based Reinforcement Learning},
author={Linsen, Dong and Guanyu, Gao and Yuanlong, Li and Yonggang, Wen},
journal={arXiv preprint arXiv:1904.10762},
year={2019}
}
```
### Report an issue
If you find any bugs on issues, please open an issue or send an email to me
(linsen001@e.ntu.edu.sg) with detailed information. I appreciate your help!
نیازمندی
| مقدار | نام |
|---|---|
| >=20.0 | pip |
| >=2.7.4 | pybullet |
| >=0.7.0 | absl-py |
| >=0.7.1 | astor |
| >=1.12.2 | cffi |
| >=3.0.4 | chardet |
| >=0.29.6 | Cython |
| >=0.17.1 | future |
| >=0.2.2 | gast |
| >=1.7.1 | glfw |
| >=1.4.0 | GPUtil |
| >=1.19.0 | grpcio |
| ==0.12.0 | gym |
| >=2.9.0 | h5py |
| >=3.13.0 | json-tricks |
| >=0.12.2 | lockfile |
| >=3.0.1 | Markdown |
| >=1.16.2 | numpy |
| >=1.9 | overrides |
| >=5.1.3 | pbr |
| >=5.4.1 | Pillow |
| >=2.19 | pycparser |
| >=1.3.2 | pyglet |
| >=3.1.0 | PyOpenGL |
| >=2.21.0 | requests |
| >=1.2.1 | scipy |
| >=1.12.0 | six |
| >=41.0.0 | setuptools |
| ==0.7.0 | tensorflow-probability |
| >=0.6.9 | transitions |
| >=2.1.0 | typeguard |
| >=1.24.2 | urllib3 |
| >=0.15.3 | Werkzeug |
| >=4.5.2 | coverage |
| >=2.0.15 | codecov |
| >=0.24.2 | pandas |
| >=1.2 | autograd |
| ==1.4.1 | gpflow |
| >=3.0.3 | matplotlib |
| >=0.9.0 | seaborn |
| ==1.0.48 | roboschool |
| >=4.1.0.25 | opencv-python |
| >=0.21.1 | scikit-learn |
| >=0.1.14 | atari-py |
زبان مورد نیاز
| مقدار | نام |
|---|---|
| >=3.5 | Python |
نحوه نصب
نصب پکیج whl baconian-0.2.6:
pip install baconian-0.2.6.whl
نصب پکیج tar.gz baconian-0.2.6:
pip install baconian-0.2.6.tar.gz