Archie C. Chapman

About

Archie C. Chapman is a researcher whose work sits at the intersection of multi-agent systems, robotics, and deep reinforcement learning, with a particular focus on bridging the gap between theoretical algorithms and real-world deployment. Chapman's most-cited contribution, "Flood Disaster Mitigation: A Real-World Challenge Problem for Multi-agent Unmanned Surface Vehicles" (2012, 28 citations), established a compelling and practically grounded benchmark for cooperative autonomous systems operating in high-stakes, unpredictable environments — a problem that remains highly relevant as climate-related disasters intensify globally. His more recent work addresses the formidable sim-to-real challenge in deep reinforcement learning, tackling issues such as partial observability in sensor data and the asynchronous, non-linear nature of physical systems that conventional simulated training fails to capture. Papers on feature extraction for robotic platforms (2023, 11 citations) and non-blocking asynchronous training frameworks (2022, 6 citations) reflect Chapman's commitment to making reinforcement learning genuinely deployable on real hardware. Together, his contributions offer students and practitioners a valuable roadmap for translating powerful machine learning methods into robust autonomous systems capable of operating reliably in the messy complexity of the physical world.

Research Focus

Key Achievements

Top Papers

1. 1
   Flood Disaster Mitigation: A Real-World Challenge Problem for Multi-agent Unmanned Surface Vehicles

   28 citations · 2012
2. 2
   Feature Extraction for Effective and Efficient Deep Reinforcement Learning on Real Robotic Platforms

   11 citations · 2023
3. 3
   Non-blocking Asynchronous Training for Reinforcement Learning in Real-World Environments

   6 citations · 2022

Key Collaborators

Contact & Links