Is a set of reinforcement learning based adaptive traffic signal control systems.
- Muh (minimalism):
- Less frameworks as possible.
- No. Reinforcement learning is not deep reinforcement learning.
- The python should approximate a papers' pseudocode.
- Data interfaces:
- Data wrangling: preprocessing, saving, loading and transforming is certain.
- For code consuming and producing data to behave in predictable ways. Data should have formal interfaces.
- Hard data interfaces constrain the loose nature of Muh.
- When in doubt follow UNIX:
- Make it easy to write, test, and run programs.
- Interactive use instead of batch processing.
- Economy and elegance of design due to size constraints ("salvation through suffering").
- Install cityflow.
- Run:
pip install -r requirements.txt.
- Invoke from the project's root directory:
python jobs/run.py