Skip to content

This project attempts to create a self driving agent over the CARLA platform using Reinforcement Learning.

Notifications You must be signed in to change notification settings

vivek-kumar9696/CarlaAutoRL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Self Driving Simulation using CARLA AI

Environment

The agent uses CARLA AI platform to using following Reinforcement Learning algorithms to train an AI model to keep a vehicle on the road and in between the lane markings

  1. DQN with HER

Sample Run

video

Run Instructions

  1. Edit settings in settings.py
  2. Run with train.py
  3. You can just play using play.py.

Future Work

  1. Create models using other algorithms such as actor critic etc.
  2. Add functionality to train and drive card towards a specified destination

About

This project attempts to create a self driving agent over the CARLA platform using Reinforcement Learning.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages