sanjulavj / multi-behavior-learning-for-socially-compatible-autonomous-driving

Proposed to leverage human driving data to learn a social preference model of human driving using inverse reinforcement learning and then integrated it with reinforcement learning-based Autonomous Vehicles policy synthesis using Social Value Orientation (SVO) theory to learn diverse levels of socially compatible driving.

Multi-behavior-Learning-for-Socially-Compatible-Autonomous-Driving

License

The implementation is based on MIT-licensed highway env and Driving-IRL-NGSIM.

multi-behavior-learning-for-socially-compatible-autonomous-driving's Issues

Code related help

Hello, thank you very much for sharing your relevant code. May I ask if you have published any corresponding articles for learning? Looking forward to your reply

How to run the code?

H, thank you very much for this work. When trying to run the code, I have some questions.
In DRL, how to run the code? Start from the sb3_highway.py?
And In the sb3_highway.py, "sys.path.insert(0, '/Users/sanjulavj/Desktop/PRj/Test Folder4 Highway/highway-env-1.3/scripts/')" , but there is no 'Test Folder4 Highway/highway-env-1.3/scripts/' in the repository.
Looking forward to your reply. Thank you！