diff --git a/.github/PARL-logo.png b/.github/PARL-logo.png
new file mode 100644
index 0000000000000000000000000000000000000000..ed9d5d50ae2261deb9b4f811522ca79c5c3ae3cd
Binary files /dev/null and b/.github/PARL-logo.png differ
diff --git a/.github/abstractions.png b/.github/abstractions.png
new file mode 100644
index 0000000000000000000000000000000000000000..5f5dffdcd9f1749eb2a03dc07ef249e8a02d18bd
Binary files /dev/null and b/.github/abstractions.png differ
diff --git a/README.md b/README.md
index 27bd133cc8921af7c1af99ad0c2ff870bef2c72f..5476837d07889f88af3b746b8d86cf85e11b4fd6 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,64 @@
-# PARL
-**Pa**ddlePaddle **R**einforcement **L**earning Framework
+<p align="center">
+<img src=".github/PARL-logo.png" alt="PARL" width="500"/>
+</p>
+
+# Features
+**Reproducible**. We provide algorithms that stably reproduce the result of many influential reinforcement learning algorithms
+
+**Large Scale**. Ability to support high performance parallelization of training with thousands of CPUs and multi-GPUs 
+
+**Reusable**.  Algorithms provided in repository could be directly adapted to a new task by defining a forward network and training mechanism will be built automatically.
+
+**Extensible**. Build new algorithms quickly by inheriting the abstract class in the framework.
+
+
+# Abstractions
+<img src=".github/abstractions.png" alt="abstractions" width="400"/>  
+PARL aims to build an agent for training algorithms to perform complex tasks.   
+The main abstractions introduced by PARL that are used to build an agent recursively are the following:
+
+### Model
+`Model` is abstracted to construct the forward network which defines a policy network or critic network given state as input.
+
+### Algorithm
+`Algorithm` describes the mechanism to update parameters in `Model` and often contains at least one model.
+
+### Agent
+`Agent` is a data bridge between environment and algorithm. It is responsible for data I/O with outside and describes data preprocessing before feeding into the training process.
+
+Here is an example of building an agent with DQN algorithm for atari games.
+```python
+import parl
+from parl.algorithms import DQN, DDQN
+
+class CriticModel(parl.Model):
+""" define specific forward model for environment ..."""
+"""
+three steps to build an agent
+   1.  define a forward model which is critic_model is this example
+   2.  a. to build a DQN algorithm, just pass the critic_model to `DQN`
+       b. to build a DDQN algorithm, just replace DQN in following line with DDQN
+   3.  define the I/O part in AtariAgent so that it could update the algorithm based on the interactive data
+"""
+
+critic_model = CriticModel(act_dim=2)
+algorithm = DQN(critic_model)
+agent = AtariAgent(aglrotihm)
+```
+
+# Install:
+### Dependencies
+- Python 2.7 or 3.5+. 
+- PaddlePaddle >=1.0 (We try to make our repository always compatible with newest version PaddlePaddle)  
+
+
+```
+pip install --upgrade git+https://github.com/PaddlePaddle/PARL.git
+```
+
+# Examples
+
+- DQN 
+- DDPG
+- PPO
+- Winning Solution for NIPS2018: AI for Prosthetics Challenge