Skip to content

Commit 25df8ab

Browse files
committed
path
2 parents 5099665 + 3d31674 commit 25df8ab

File tree

6 files changed

+88
-37
lines changed

6 files changed

+88
-37
lines changed

README.md

Lines changed: 25 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,8 @@
1515
RLzoo is a collection of the most practical reinforcement learning algorithms, frameworks and applications. It is implemented with Tensorflow 2.0 and API of neural network layers in TensorLayer 2, to provide a hands-on fast-developing approach for reinforcement learning practices and benchmarks. It supports basic toy-tests like [OpenAI Gym](https://gym.openai.com/) and [DeepMind Control Suite](https://github.com/deepmind/dm_control) with very simple configurations. Moreover, RLzoo supports robot learning benchmark environment [RLBench](https://github.com/stepjam/RLBench) based on [Vrep](http://www.coppeliarobotics.com/)/[Pyrep](https://github.com/stepjam/PyRep) simulator. Other large-scale distributed training framework for more realistic scenarios with [Unity 3D](https://github.com/Unity-Technologies/ml-agents),
1616
[Mujoco](http://www.mujoco.org/), [Bullet Physics](https://github.com/bulletphysics/bullet3), etc, will be supported in the future. A [Springer textbook](https://deepreinforcementlearningbook.org) is also provided, you can get the free PDF if your institute has Springer license.
1717

18+
Different from RLzoo for simple usage with **high-level APIs**, we also have a [RL tutorial](https://github.com/tensorlayer/tensorlayer/tree/master/examples/reinforcement_learning) that aims to make the reinforcement learning tutorial simple, transparent and straight-forward with **low-level APIs**, as this would not only benefits new learners of reinforcement learning, but also provide convenience for senior researchers to testify their new ideas quickly.
19+
1820
<!-- <em>Gym: Atari</em> <em>Gym: Box2D </em> <em>Gym: Classic Control </em> <em>Gym: MuJoCo </em>-->
1921

2022
<img src="https://github.com/tensorlayer/RLzoo/blob/master/gif/atari.gif" height=250 width=210 > <img src="https://github.com/tensorlayer/RLzoo/blob/master/gif/box2d.gif" height=250 width=210 > <img src="https://github.com/tensorlayer/RLzoo/blob/master/gif/classic.gif" height=250 width=210 > <img src="https://github.com/tensorlayer/RLzoo/blob/master/gif/mujoco.gif" height=250 width=210 >
@@ -25,9 +27,6 @@ RLzoo is a collection of the most practical reinforcement learning algorithms, f
2527

2628

2729

28-
29-
30-
3130
We aim to make it easy to configure for all components within RL, including replacing the networks, optimizers, etc. We also provide automatically adaptive policies and value functions in the common functions: for the observation space, the vector state or the raw-pixel (image) state are supported automatically according to the shape of the space; for the action space, the discrete action or continuous action are supported automatically according to the shape of the space as well. The deterministic or stochastic property of policy needs to be chosen according to each algorithm. Some environments with raw-pixel based observation (e.g. Atari, RLBench) may be hard to train, be patient and play around with the hyperparameters!
3231

3332
**Table of contents:**
@@ -44,14 +43,13 @@ We aim to make it easy to configure for all components within RL, including repl
4443
- [Credits](#credits)
4544
- [Citing](#citing)
4645

47-
Please note that this repository using RL algorithms with **high-level API**. So if you want to get familiar with each algorithm more quickly, please look at our **[RL tutorials](https://github.com/tensorlayer/tensorlayer/tree/master/examples/reinforcement_learning)** where each algorithm is implemented individually in a more straightforward manner.
4846

4947
## Status: Release
5048
We are currently open to any suggestions or pull requests from the community to make RLzoo a better repository. Given the scope of this project, we expect there could be some issues over
5149
the coming months after initial release. We will keep improving the potential problems and commit when significant changes are made in the future. Current default hyperparameters for each algorithm and each environment may not be optimal, so you can play around with those hyperparameters to achieve best performances. We will release a version with optimal hyperparameters and benchmark results for all algorithms in the future.
5250

53-
## Contents:
54-
### Algorithms:
51+
## Contents
52+
### Algorithms
5553

5654
| Algorithms | Papers |
5755
| --------------- | -------|
@@ -76,7 +74,7 @@ the coming months after initial release. We will keep improving the potential pr
7674
|Twin Delayed DDPG (TD3)|[Addressing function approximation error in actor-critic methods. Fujimoto et al. 2018.](https://arxiv.org/pdf/1802.09477.pdf)|
7775
|Soft Actor-Critic (SAC)|[Soft actor-critic algorithms and applications. Haarnoja et al. 2018.](https://arxiv.org/abs/1812.05905)|
7876

79-
### Environments:
77+
### Environments
8078

8179
* [**OpenAI Gym**](https://gym.openai.com/):
8280

@@ -126,7 +124,7 @@ The supported configurations for RL algorithms with corresponding environments i
126124
| TRPO | Discrete/Continuous | Stochastic | On-policy | All |
127125

128126

129-
## Prerequisites:
127+
## Prerequisites
130128

131129
* python >=3.5 (python 3.6 is needed if using dm_control)
132130
* tensorflow >= 2.0.0 or tensorflow-gpu >= 2.0.0a0
@@ -136,15 +134,17 @@ The supported configurations for RL algorithms with corresponding environments i
136134
* [Mujoco 2.0](http://www.mujoco.org/), [dm_control](https://github.com/deepmind/dm_control), [dm2gym](https://github.com/zuoxingdong/dm2gym) (if using DeepMind Control Suite environments)
137135
* Vrep, PyRep, RLBench (if using RLBench environments, follows [here](http://www.coppeliarobotics.com/downloads.html), [here](https://github.com/stepjam/PyRep) and [here](https://github.com/stepjam/RLBench))
138136

139-
## Installation:
137+
## Installation
140138

141139
To install RLzoo package with key requirements:
142140

143141
```
144142
pip install rlzoo
145143
```
146144

147-
## Usage:
145+
## Usage
146+
147+
For usage, please check our [online documentation](https://rlzoo.readthedocs.io).
148148

149149
### 0. Quick Start
150150
Choose whatever environments with whatever RL algorithms supported in RLzoo, and enjoy the game by running following example in the root file of installed package:
@@ -187,7 +187,6 @@ alg.learn(env=env, mode='train', render=False, **learn_params)
187187
alg.learn(env=env, mode='test', render=True, **learn_params)
188188
```
189189

190-
#### To Run:
191190

192191
```python
193192
# in the root folder of rlzoo package
@@ -199,7 +198,7 @@ python run_rlzoo.py
199198

200199
RLzoo with **explicit configurations** means the configurations for learning, including parameter values for the algorithm and the learning process, the network structures used in the algorithms and the optimizers etc, are explicitly displayed in the main script for running. And the main scripts for demonstration are under the folder of each algorithm, for example, `./rlzoo/algorithms/sac/run_sac.py` can be called with `python algorithms/sac/run_sac.py` from the file `./rlzoo` to run the learning process same as in above implicit configurations.
201200

202-
#### A Quick Example:
201+
#### A Quick Example
203202

204203
```python
205204
import gym
@@ -264,8 +263,6 @@ render: if true, visualize the environment
264263
model.learn(env, test_episodes=100, max_steps=200, mode='test', render=True)
265264
```
266265

267-
#### To Run:
268-
269266
In the package folder, we provides examples with explicit configurations for each algorithm.
270267

271268
```python
@@ -276,23 +273,23 @@ python algorithms/<ALGORITHM_NAME>/run_<ALGORITHM_NAME>.py
276273
python algorithms/ac/run_ac.py
277274
```
278275

279-
## Troubleshooting:
276+
## Troubleshooting
280277

281278
* If you meet the error *'AttributeError: module 'tensorflow' has no attribute 'contrib''* when running the code after installing tensorflow-probability, try:
282279
`pip install --upgrade tf-nightly-2.0-preview tfp-nightly`
283280
* When trying to use RLBench environments, *'No module named rlbench'* can be caused by no RLBench package installed at your local or a mistake in the python path. You should add `export PYTHONPATH=/home/quantumiracle/research/vrep/PyRep/RLBench` every time you try to run the learning script with RLBench environment or add it to you `~/.bashrc` file once for all.
284281
* If you meet the error that the Qt platform is not loaded correctly when using DeepMind Control Suite environments, it's probably caused by your Ubuntu system not being version 14.04 or 16.04. Check [here](https://github.com/deepmind/dm_control).
285282

286-
## Credits:
287-
Our contributors include:
283+
## Credits
284+
Our core contributors include:
288285

289286
[Zihan Ding](https://github.com/quantumiracle?tab=repositories),
290287
[Tianyang Yu](https://github.com/Tokarev-TT-33),
291288
[Yanhua Huang](https://github.com/Officium),
292289
[Hongming Zhang](https://github.com/initial-h),
293290
[Hao Dong](https://github.com/zsdonghao)
294291

295-
## Citing:
292+
## Citing
296293

297294
```
298295
@misc{RLzoo,
@@ -305,6 +302,16 @@ Our contributors include:
305302
}
306303
```
307304

305+
## Other Resources
306+
<br/>
307+
<a href="https://deepreinforcementlearningbook.org" target="\_blank">
308+
<div align="center">
309+
<img src="http://deep-reinforcement-learning-book.github.io/assets/images/cover_v1.png" width="20%"/>
310+
</div>
311+
<!-- <div align="center"><caption>Slack Invitation Link</caption></div> -->
312+
</a>
313+
<br/>
314+
308315
<br/>
309316
<a href="https://deepreinforcementlearningbook.org" target="\_blank">
310317
<div align="center">

docs/guide/quickstart.rst

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,6 +30,5 @@ Open ``./run_rlzoo.py``:
3030
Run the example:
3131

3232
.. code-block:: bash
33-
:linenos:
3433
3534
python run_rlzoo.py

docs/index.rst

Lines changed: 3 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -6,8 +6,6 @@
66
Reinforcement Learning Zoo for Simple Usage
77
============================================
88

9-
10-
119
.. image:: img/logo.png
1210
:width: 50 %
1311
:align: center
@@ -44,11 +42,11 @@ RLzoo is a collection of the most practical reinforcement learning algorithms, f
4442
common/common
4543

4644
.. toctree::
47-
:maxdepth: 2
45+
:maxdepth: 1
4846
:caption: Other Resources
4947

50-
other/drlbook
51-
48+
other/drl_book
49+
other/drl_tutorial
5250

5351
Contributing
5452
==================
@@ -63,17 +61,6 @@ Citation
6361
* :ref:`search`
6462

6563

66-
Other Resources
67-
==================
68-
69-
70-
.. image:: http://deep-reinforcement-learning-book.github.io/assets/images/cover_v1.png
71-
:width: 30 %
72-
:target: https://deepreinforcementlearningbook.org
73-
.. image:: http://download.broadview.com.cn/ScreenShow/180371146440fada4ad2
74-
:width: 30 %
75-
:target: http://www.broadview.com.cn/book/5059
76-
7764
.. image:: img/logo.png
7865
:width: 70 %
7966
:align: center

docs/other/drl_book.rst

Lines changed: 42 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,42 @@
1+
DRL Book
2+
==========
3+
4+
.. image:: http://deep-reinforcement-learning-book.github.io/assets/images/cover_v1.png
5+
:width: 30 %
6+
:align: center
7+
:target: https://deepreinforcementlearningbook.org
8+
9+
- You can get the `free PDF <https://deepreinforcementlearningbook.org>`__ if your institute has Springer license.
10+
11+
Deep reinforcement learning (DRL) relies on the intersection of reinforcement learning (RL) and deep learning (DL). It has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine and famously contributed to the success of AlphaGo. Furthermore, it opens up numerous new applications in domains such as healthcare, robotics, smart grids, and finance.
12+
13+
Divided into three main parts, this book provides a comprehensive and self-contained introduction to DRL. The first part introduces the foundations of DL, RL and widely used DRL methods and discusses their implementation. The second part covers selected DRL research topics, which are useful for those wanting to specialize in DRL research. To help readers gain a deep understanding of DRL and quickly apply the techniques in practice, the third part presents mass applications, such as the intelligent transportation system and learning to run, with detailed explanations.
14+
15+
The book is intended for computer science students, both undergraduate and postgraduate, who would like to learn DRL from scratch, practice its implementation, and explore the research topics. This book also appeals to engineers and practitioners who do not have strong machine learning background, but want to quickly understand how DRL works and use the techniques in their applications.
16+
17+
Editors
18+
--------
19+
- Hao Dong - Peking University
20+
- Zihan Ding - Princeton University
21+
- Shanghang Zhang - University of California, Berkeley
22+
23+
Authors
24+
--------
25+
- Hao Dong - Peking University
26+
- Zihan Ding - Princeton University
27+
- Shanghang Zhang - University of California, Berkeley
28+
- Hang Yuan - Oxford University
29+
- Hongming Zhang - Peking University
30+
- Jingqing Zhang - Imperial College London
31+
- Yanhua Huang - Xiaohongshu Technology Co.
32+
- Tianyang Yu - Nanchang University
33+
- Huaqing Zhang - Google
34+
- Ruitong Huang - Borealis AI
35+
36+
37+
.. image:: https://deep-generative-models.github.io/files/web/water-bottom-min.png
38+
:width: 100 %
39+
:align: center
40+
:target: https://github.com/tensorlayer/tensorlayer/edit/master/examples/reinforcement_learning
41+
42+

docs/other/drl_tutorial.rst

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
DRL Tutorial
2+
=================================
3+
4+
5+
.. image:: https://tensorlayer.readthedocs.io/en/latest/_images/tl_transparent_logo.png
6+
:width: 30 %
7+
:align: center
8+
:target: https://github.com/tensorlayer/tensorlayer/edit/master/examples/reinforcement_learning
9+
10+
11+
Different from RLzoo for simple usage with **high-level APIs**, the `RL tutorial <https://github.com/tensorlayer/tensorlayer/edit/master/examples/reinforcement_learning>`__ aims to make the reinforcement learning tutorial simple, transparent and straight-forward with **low-level APIs**, as this would not only benefits new learners of reinforcement learning, but also provide convenience for senior researchers to testify their new ideas quickly.
12+
13+
.. image:: https://deep-generative-models.github.io/files/web/water-bottom-min.png
14+
:width: 100 %
15+
:align: center
16+
:target: https://github.com/tensorlayer/tensorlayer/edit/master/examples/reinforcement_learning
17+
18+

docs/other/drlbook.rst

Lines changed: 0 additions & 2 deletions
This file was deleted.

0 commit comments

Comments
 (0)