Scalable Multi-Agent RL Training School for Autonomous Driving
Role in this project:
Back-end Developer Contributions:34 releases, 1642 reviews, 1572 commits in 2 years 4 months
Contributions summary:Alban primarily addressed issues related to memory leaks and other bugs within the `smarts` project. They identified and fixed scenarios where envision logs were not properly handled, and also resolved cases where envision failed to connect or where scenario iterators were caching scenarios, leading to potential resource exhaustion. Additionally, the user added functionality to provide accelerometer sensor data and updated the environment to use a per-user log file. They also contributed to upgrades to the tensorflow versions and several versioning changes to the repository.
autonomous-drivingmulti-agentreinforcement-learningpythonsimulator
Contributions:23 pushes in 1 year 9 months