/Autonomous-Drone-Navigation-TD3-vs-SAC

Comparative Study of Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) for Autonomous Drone Navigation using ROS and Gazebo. This project explores the performance of these algorithms in complex environments, focusing on navigation efficiency, obstacle avoidance, and learning efficiency.

Primary LanguagePythonMIT LicenseMIT

Stargazers