Add video link to document (#69)

* Update video * update readme * update readme * update readme
metadriverse · Sep 7, 2021 · 8d02413 · 8d02413
1 parent cf6f028
commit 8d02413
Show file tree

Hide file tree

Showing 4 changed files with 78 additions and 41 deletions.
diff --git a/README.md b/README.md
@@ -10,11 +10,9 @@
 <div style="text-align: center; width:100%; margin: 0 auto; display: inline-block">
 <strong>
 [
-<a href="https://decisionforce.github.io/metadrive/">Website</a>
-|
 <a href="https://metadrive-simulator.readthedocs.io">Documentation</a>
 |
-<a href="">Demo Video (TBD)</a>
+<a href="https://www.youtube.com/embed/3ziJPqC_-T4">Demo Video</a>
 ]
 </strong>
 </div>
@@ -79,12 +77,12 @@ python -m metadrive.examples.drive_in_multi_agent_env --pygame_render --env roun
 ```
 
 env argument could be:
-- roundabout (default)
-- intersection
-- tollgate
-- bottleneck
-- parkinglot
-- pgmap
+- `roundabout` (default)
+- `intersection`
+- `tollgate`
+- `bottleneck`
+- `parkinglot`
+- `pgmap`
 
 Run the example of procedural generation of a new map as:
 
@@ -119,33 +117,6 @@ env.close()
 ```
 
 
-## 📦 Predefined environment sets
-
-We define several standard MetaDrive Gym environments, where the user can start training off the shelf:
-
-```python
-import gym
-import metadrive  # Register the environment
-
-env = gym.make("MetaDrive-v0")
-```
-
-The following table presents the names for the predefined environments. 
-
-|&nbsp;  Gym Environment Name   | Random Seed Range | Number of Maps | Comments                                          |
-| ----------------------- | ----------------- | -------------- | ------------------------------------------------------- |
-| `MetaDrive-test-v0`       | [0, 200)          | 200            | Test set, not change for all experiments.               |
-| `MetaDrive-validation-v0` &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;|[200, 1000)|800| Validation set.|
-| `MetaDrive-v0`            | [1000, 1100)      | 100            | Default training setting, for quick start.              |
-| `MetaDrive-10envs-v0`     | [1000, 1100)      | 10             | Training environment with 10 maps.                      |
-| `MetaDrive-1000envs-v0`   | [1000, 1100)      | 1000           | Training environment with 1000 maps.                    |
-| `MetaDrive-training0-v0`  | [3000, 4000)      | 1000           | First set of 1000 environments.                         |
-| `MetaDrive-training1-v0`  | [5000, 6000)      | 1000           | Second set of 1000 environments.                        |
-| `MetaDrive-training2-v0`  | [7000, 8000)      | 1000           | Thirds set of 1000 environments.                        |
-| ...                     |                   |                | *More map set and environments will be added* |
-
-
-
 ## 🏫 Documentations
 
 Find more details in: [MetaDrive](https://metadrive-simulator.readthedocs.io)

diff --git a/documentation/source/index.rst b/documentation/source/index.rst
@@ -12,13 +12,14 @@
 MetaDrive Documentation
 ########################
 
+
 Welcome to the MetaDrive documentation!
-MetaDrive is an efficient and compositional driving simulator for reinforcement learning community!
-The key features of MetaDrive includes:
+MetaDrive is an efficient and compositional driving simulator with the following key features:
+
+* Compositional: It supports generating infinite scenes with various road maps and traffic settings for the research of generalizable RL.
+* Lightweight: It is easy to install and run. It can run up to 300 FPS on a standard PC.
+* Realistic: Accurate physics simulation and multiple sensory input including Lidar, RGB images, top-down semantic map and first-person view images.
 
-- **Lightweight**: Extremely easy to download, install and run in almost all platforms. Up to 300 simulation step per second and easy to parallel.
-- **Realistic**: Accurate physics simulation and multiple sensory input including Lidar, sensory data, top-down semantic map and first-person view images.
-- **Compositional**: Support generating infinite scenes and configuring various traffics, vehicles, and environmental settings.
 
 This documentation brings you the information on installation, usages and more of MetaDrive!
 
@@ -60,3 +61,17 @@ Please feel free to contact us if you have any suggestions or ideas!
 
    concept.rst
    development.rst
+
+
+.. raw:: html
+
+    <br>
+    <table width="100%" style="margin: 0 0; text-align: center;">
+        <tr>
+            <td>
+            <iframe width="560" height="315" src="https://www.youtube.com/embed/3ziJPqC_-T4" title="MetaDrive Introduction" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+            </td>
+        </tr>
+    </table>
+
+
diff --git a/documentation/source/read_data_from_dataset.rst b/documentation/source/read_data_from_dataset.rst
@@ -5,6 +5,18 @@
 Read Data from Dataset
 ########################
 
+.. raw:: html
+
+    <br>
+    <table width="100%" style="margin: 0 0; text-align: center;">
+        <tr>
+            <td>
+            <iframe width="560" height="315" src="https://www.youtube.com/embed/EbC6-grcmRY" title="MetaDrive Multi-agent Environments" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+            </td>
+        </tr>
+    </table>
+    <br>
+
 
 Setting up Argoverse dataset
 #############################

diff --git a/documentation/source/rl_environments.rst b/documentation/source/rl_environments.rst
@@ -5,9 +5,23 @@ Existing RL Environments
 ##########################
 
 
+
 Generalization Environments
 ###############################
 
+.. raw:: html
+
+    <br>
+    <table width="100%" style="margin: 0 0; text-align: center;">
+        <tr>
+            <td>
+            <iframe width="560" height="315" src="https://www.youtube.com/embed/hL0XDfNHYjA" title="MetaDrive Generalization Environments" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+            </td>
+        </tr>
+    </table>
+    <br>
+
+
 
 To benchmark the generalizability of a driving policy, we develop an RL environment that can generate an unlimited number of diverse driving scenarios through procedural generation.
 The following script creates a basic environment that can be used for such purpose:
@@ -46,6 +60,19 @@ In this case, the scenarios generated by random seeds [1000, 1999] will be used
 Safety Environments
 #####################
 
+.. raw:: html
+
+    <br>
+    <table width="100%" style="margin: 0 0; text-align: center;">
+        <tr>
+            <td>
+            <iframe width="560" height="315" src="https://www.youtube.com/embed/6YNgwxEvYtg" title="MetaDrive Safety Environments" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+            </td>
+        </tr>
+    </table>
+    <br>
+
+
 Safety is a major concern for the trial-and-error nature of RL.
 As driving itself is a safety-critical application, it is essential to evaluate the constrained optimization methods under the domain of autonomous driving.
 We therefore define a new suite of environments to benchmark the **safe exploration** in RL.
@@ -79,6 +106,18 @@ Try the following script to drive in the Safe RL environments.
 Multi-agent Environments
 #########################
 
+.. raw:: html
+
+    <br>
+    <table width="100%" style="margin: 0 0; text-align: center;">
+        <tr>
+            <td>
+            <iframe width="560" height="315" src="https://www.youtube.com/embed/1-sXZv2ZzXM" title="MetaDrive Multi-agent Environments" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+            </td>
+        </tr>
+    </table>
+    <br>
+
 As shown in the above figure,
 we develop a set of environments to evaluate MARL methods for simulating traffic flow.
 The descriptions and typical settings of the six traffic environments are as follows: