2 papers
cs.AI2025
Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control
Hazim Alzorgan, Abolfazl Razi
Actor-critic methods, like Twin Delayed Deep Deterministic Policy Gradient (TD3), depend on basic noise-based exploration, which can result in less than optimal policy convergence.…
cs.RO2023
Actuator Trajectory Planning for UAVs with Overhead Manipulator using Reinforcement Learning
Hazim Alzorgan, Abolfazl Razi, Ata Jahangir Moshayedi
In this paper, we investigate the operation of an aerial manipulator system, namely an Unmanned Aerial Vehicle (UAV) equipped with a controllable arm with two degrees of freedom to…