You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+25-18Lines changed: 25 additions & 18 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,6 +15,8 @@
15
15
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),
16
16
[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.
17
17
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.
@@ -25,9 +27,6 @@ RLzoo is a collection of the most practical reinforcement learning algorithms, f
25
27
26
28
27
29
28
-
29
-
30
-
31
30
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!
32
31
33
32
**Table of contents:**
@@ -44,14 +43,13 @@ We aim to make it easy to configure for all components within RL, including repl
44
43
-[Credits](#credits)
45
44
-[Citing](#citing)
46
45
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.
48
46
49
47
## Status: Release
50
48
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
51
49
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.
52
50
53
-
## Contents:
54
-
### Algorithms:
51
+
## Contents
52
+
### Algorithms
55
53
56
54
| Algorithms | Papers |
57
55
| --------------- | -------|
@@ -76,7 +74,7 @@ the coming months after initial release. We will keep improving the potential pr
76
74
|Twin Delayed DDPG (TD3)|[Addressing function approximation error in actor-critic methods. Fujimoto et al. 2018.](https://arxiv.org/pdf/1802.09477.pdf)|
77
75
|Soft Actor-Critic (SAC)|[Soft actor-critic algorithms and applications. Haarnoja et al. 2018.](https://arxiv.org/abs/1812.05905)|
78
76
79
-
### Environments:
77
+
### Environments
80
78
81
79
*[**OpenAI Gym**](https://gym.openai.com/):
82
80
@@ -126,7 +124,7 @@ The supported configurations for RL algorithms with corresponding environments i
* python >=3.5 (python 3.6 is needed if using dm_control)
132
130
* tensorflow >= 2.0.0 or tensorflow-gpu >= 2.0.0a0
@@ -136,15 +134,17 @@ The supported configurations for RL algorithms with corresponding environments i
136
134
*[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)
137
135
* 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))
138
136
139
-
## Installation:
137
+
## Installation
140
138
141
139
To install RLzoo package with key requirements:
142
140
143
141
```
144
142
pip install rlzoo
145
143
```
146
144
147
-
## Usage:
145
+
## Usage
146
+
147
+
For usage, please check our [online documentation](https://rlzoo.readthedocs.io).
148
148
149
149
### 0. Quick Start
150
150
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:
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.
201
200
202
-
#### A Quick Example:
201
+
#### A Quick Example
203
202
204
203
```python
205
204
import gym
@@ -264,8 +263,6 @@ render: if true, visualize the environment
* If you meet the error *'AttributeError: module 'tensorflow' has no attribute 'contrib''* when running the code after installing tensorflow-probability, try:
* 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.
284
281
* 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).
- 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
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.
0 commit comments