This study applies the Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) framework to autonomous driving, focusing on the car-following scenario. The primary objective is to extract the driver's reward function from a dataset of expert demonstrations. We leverage deep neural networks to approximate the reward function, capitalizing on their ability to represent complex, nonlinear interdependencies of state features.
-
Notifications
You must be signed in to change notification settings - Fork 0
Applying Max Entropy Deep Inverse Reinforcement Learning (Wulfmeier 2015) to Car Following
llmvetter/irl_car_following
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Applying Max Entropy Deep Inverse Reinforcement Learning (Wulfmeier 2015) to Car Following
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published