Curriculum-Based Adversarial Heterogeneous Agent Reinforcement Learning for Autonomous Quad-Copter Landing in Maritime Settings
Simulated mid-air capture of quadrotor UAVs by a ship-mounted robotic arm is studied, learning robust cooperative control policies with Heterogeneous-Agent Proximal Policy Optimization (HAPPO) Reinforcement Learning.
A. Nguyen, Sree Showrya Kotala, Stefan Banioi-Crijman et al.
· 0 citations