Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Introduce a SimGen example #791

Merged
merged 10 commits into from
Dec 17, 2024
Merged

Introduce a SimGen example #791

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
37e27e6
Clean code
pengzhenghao Dec 16, 2024
38517a0
clean README
pengzhenghao Dec 16, 2024
8ec5462
Add a simgen render notebook
pengzhenghao Dec 16, 2024
d09cbc4
Add simgenrender example
pengzhenghao Dec 16, 2024
672f7e3
Up
pengzhenghao Dec 16, 2024
6a01225
Fix
pengzhenghao Dec 16, 2024
35aa375
update
pengzhenghao Dec 16, 2024
d7c7664
Fix
pengzhenghao Dec 16, 2024
45831ba
Trying to fix test by using smaller depth image
pengzhenghao Dec 17, 2024
92ef53e
format
pengzhenghao Dec 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
80 changes: 0 additions & 80 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,27 +102,7 @@ Traffic vehicles can not response to surrounding vchicles if directly replaying
Add argument ```--reactive_traffic``` to use an IDM policy control them and make them reactive.
Press key ```r``` for loading a new scenario, and ```b``` or ```q``` for switching perspective.

[comment]: <> (### LQY: avoid introducing these trivial things )

[comment]: <> (Run the example of procedural generation of a new map as:)

[comment]: <> (```bash)

[comment]: <> (python -m metadrive.examples.procedural_generation)

[comment]: <> (```)

[comment]: <> (*Note that the scripts above can not be run in a headless machine.*)

[comment]: <> (*Please refer to the installation guideline in documentation for more information about how to launch runing in a headless machine.*)

[comment]: <> (Run the following command to draw the generated maps from procedural generation:)

[comment]: <> (```bash)

[comment]: <> (python -m metadrive.examples.draw_maps)

[comment]: <> (```)

### Basic Usage
To build the RL environment in python script, you can simply code in the Farama Gymnasium format as:
Expand Down Expand Up @@ -167,66 +147,6 @@ If you use MetaDrive in your own work, please cite:
}
```

## 🎉 Relevant Projects

**Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization**
\
Zhenghao Peng, Quanyi Li, Chunxiao Liu, Bolei Zhou
\
*NeurIPS 2021*
\
[<a href="https://arxiv.org/pdf/2110.13827.pdf" target="_blank">Paper</a>]
[<a href="https://github.com/decisionforce/CoPO" target="_blank">Code</a>]
[<a href="https://decisionforce.github.io/CoPO" target="_blank">Webpage</a>]
[<a href="https://decisionforce.github.io/CoPO/copo_poster.pdf" target="_blank">Poster</a>]
[<a href="https://youtu.be/sOw43l8lwxE" target="_blank">Talk</a>]
[<a href="https://github.com/metadriverse/metadrive-benchmark/tree/main/MARL" target="_blank">Results&Models</a>]


**Safe Driving via Expert Guided Policy Optimization**
\
Zhenghao Peng*, Quanyi Li*, Chunxiao Liu, Bolei Zhou
\
*Conference on Robot Learning (CoRL) 2021*
\
[<a href="https://arxiv.org/pdf/2110.06831.pdf" target="_blank">Paper</a>]
[<a href="https://github.com/decisionforce/EGPO" target="_blank">Code</a>]
[<a href="https://decisionforce.github.io/EGPO/" target="_blank">Webpage</a>]
[<a href="https://decisionforce.github.io/EGPO/images/egpo_poster.png" target="_blank">Poster</a>]

**Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization**
\
Quanyi Li*, Zhenghao Peng*, Bolei Zhou
\
*ICLR 2022*
\
[<a href="https://arxiv.org/pdf/2202.10341.pdf" target="_blank">Paper</a>]
[<a href="https://github.com/decisionforce/HACO" target="_blank">Code</a>]
[<a href="https://decisionforce.github.io/HACO/" target="_blank">Webpage</a>]
[<a href="https://github.com/decisionforce/HACO/blob/main/docs/iclr_poster.pdf" target="_blank">Poster</a>]
[<a href="https://youtu.be/PiJv4wtp8T8" target="_blank">Talk</a>]

**Human-AI Shared Control via Policy Dissection**
\
Quanyi Li, Zhenghao Peng, Haibin Wu, Lan Feng, Bolei Zhou
\
*NeurIPS 2022*
\
[<a href="https://arxiv.org/pdf/2206.00152.pdf" target="_blank">Paper</a>]
[<a href="https://github.com/metadriverse/policydissect" target="_blank">Code</a>]
[<a href="https://metadriverse.github.io/policydissect/" target="_blank">Webpage</a>]


And more:


* Yang, Yujie, Yuxuan Jiang, Yichen Liu, Jianyu Chen, and Shengbo Eben Li. "Model-Free Safe Reinforcement Learning through Neural Barrier Certificate." IEEE Robotics and Automation Letters (2023).

* Feng, Lan, Quanyi Li, Zhenghao Peng, Shuhan Tan, and Bolei Zhou. "TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios." (**ICRA 2023**)

* Zhenghai Xue, Zhenghao Peng, Quanyi Li, Zhihan Liu, Bolei Zhou. "Guarded Policy Optimization with Imperfect Online Demonstrations." (**ICLR 2023**)



## Acknowledgement

Expand Down
1 change: 1 addition & 0 deletions documentation/source/index.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,7 @@ Please feel free to contact us if you have any suggestions or ideas!
navigation.ipynb
scenario_description.ipynb
record_replay.ipynb
simgen_render.ipynb

.. toctree::
:hidden:
Expand Down
4 changes: 1 addition & 3 deletions documentation/source/install.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,7 @@ We recommend to use the command following to install::
.. note:: Using ``git clone https://github.com/metadriverse/metadrive.git --single-branch``
will only pull the main branch and bypass other branches, saving disk space.

It is also allowed to install MetaDrive via pip.However, it is possible that some latest features and bug fixings are not available through PyPI installation::

pip install metadrive-simulator
.. note:: We don't recommend installing MetaDrive with ``pip install metadrive-simulator`` because it will download the source code from PyPI, which may not be the latest version.



Expand Down
Loading
Loading