search

mschrader15 / reinforcement-learning-sumo

Reinforcement Learning + traffic microsimulation (via SUMO). Uses Ray RLLIB and forces SUMO into the OpenAI Gym Framework
https://maxschrader.io/reinforcement-learning-and-sumo
47 stars 9 forks source link

How to train, run this model #1

Closed TrinhTuanHung2021 closed 2 years ago

TrinhTuanHung2021 commented 2 years ago

Hello Thank you for sharing your code. But Could you show me how to train and test this model? Thanks

mschrader15 commented 2 years ago

Hi @TrinhTuanHung2021 , thanks for looking at the repository!

Do you have a specific goal in mind? There are several RL + SUMO codebases available and I want to make sure that mine is the right one for you to use first.

TrinhTuanHung2021 commented 2 years ago

Hi @TrinhTuanHung2021 , thanks for looking at the repository!

Do you have a specific goal in mind? There are several RL + SUMO codebases available and I want to make sure that mine is the right one for you to use first.

Thank you for sharing the coding. I already know Sumo and flow for applying DRL to traffic simulation. PPO is an interesting topic for traffic but very difficult. So I think to understand your model deeply, there should be specific and detailed instructions attached. You can clearly share every step from training to testing for user convenience

mschrader15 commented 2 years ago

There is a more detailed write-up here: https://maxschrader.io/reinforcement-learning-and-sumo

Let me know if you want more information!