idreesshaikh/Autonomous-Driving-in-Carla-using-Deep-Reinforcement-Learning
A deep reinforcement learning project that trains a PPO agent to drive autonomously in the CARLA simulator using camera observations compressed through a VAE.
Velocity · 7d
+0.4
★ / day
Trend
→steady
star history
The project implements a PPO-based autonomous driving agent using the CARLA simulation environment. It processes raw camera observations through a Variational Autoencoder to compress high-dimensional inputs into a lower-dimensional latent space, which accelerates policy learning. The agent learns to navigate predetermined routes and avoid collisions in a simulated urban environment.