Target localization using Multi-Agent Deep Reinforcement Learning with Proximal Policy Optimization

Ahmed Alagha, Shakti Singh, Rabeb Mizouni, Jamal Bentahar, Hadi Otrok

Abstract: Highlights•Cooperative target localization can be achieved using MDRL with team-based rewards.•Learning scalability with centralized learning and distributed execution.•Cooperation is necessary for quick localization and resource management.•Reinforcement Learning provides adaptable solutions for complex environments.