Update doc

README.md

@@ -11,6 +11,16 @@ Related paper:
 
 <a href="https://youtu.be/qNsHMkIsqJc"><img src="imgs/rl_toolboxplay.jpg"/></a>
 
+## Main Features
+
+- 10 RL algorithms ([Stable Baselines](https://github.com/hill-a/stable-baselines) included)
+- logging / plotting / visdom integration / replay trained agent
+- hyperparameter search (hyperband, hyperopt)
+- integration with State Representation Learning (SRL) methods (for feature extraction)
+- visualisation tools (explore latent space, display action proba, live plot in the state space, ...)
+- robotics environments to compare SRL methods
+- easy install using anaconda env or Docker images (CPU/GPU)
+
 ## Documentation
 
 Documentation is available online: [https://s-rl-toolbox.readthedocs.io/](https://s-rl-toolbox.readthedocs.io/)
@@ -20,7 +30,7 @@ Documentation is available online: [https://s-rl-toolbox.readthedocs.io/](https:
 
 **Python 3 is required** (python 2 is not supported because of OpenAI baselines)
 
-Note: we are using [Stable Baselines](https://github.com/hill-a/stable-baselines.git), a fork of OpenAI Baselines with unified interface and other improvements (e.g. tensorboard support).
+Note: we are using [Stable Baselines](https://github.com/hill-a/stable-baselines), a fork of OpenAI Baselines with unified interface and other improvements (e.g. tensorboard support).
 
 
 ### Using Anaconda

docs/guide/quickstart.rst

@@ -0,0 +1,20 @@
+.. _quickstart:
+
+Getting Started
+===============
+
+Here is a quick example of how to train a PPO2 agent on Mobile Robot environment for 10 000 steps using 4 parallel processes:
+
+::
+
+  python -m rl_baselines.train --algo ppo2 --no-vis --num-cpu 4 --num-timesteps 10000 --env MobileRobotGymEnv-v0
+
+
+The complete command (logs will be saved in `logs/` folder):
+
+::
+
+  python -m rl_baselines.train --algo rl_algo --env env1 --log-dir logs/ --srl-model raw_pixels --num-timesteps 10000 --no-vis
+
+
+To use the robot's position as input instead of pixels, just pass `--srl-model ground_truth` instead of `--srl-model raw_pixels`

docs/index.rst

@@ -23,6 +23,21 @@ We also release customizable Gym environments for working with
 simulation (Kuka arm, Mobile Robot in PyBullet, running at 250 FPS on a
 8-core machine) and real robots (Baxter Robot, Robobo with ROS).
 
+Main Features
+-------------
+
+-  10 RL algorithms (`Stable Baselines`_ included)
+-  logging / plotting / visdom integration / replay trained agent
+-  hyperparameter search (hyperband, hyperopt)
+-  integration with State Representation Learning (SRL) methods (for
+   feature extraction)
+-  visualisation tools (explore latent space, display action proba, live
+   plot in the state space, …)
+-  robotics environments to compare SRL methods
+-  easy install using anaconda env or Docker images (CPU/GPU)
+
+.. _Stable Baselines: https://github.com/hill-a/stable-baselines
+
 Related paper:
 
 -  "S-RL Toolbox: Environments, Datasets and Evaluation Metrics for
@@ -35,6 +50,7 @@ Related paper:
    :caption: Guide
 
    guide/install
+   guide/quickstart
    guide/rl
    guide/hyperparams
    guide/envs