Joshua Riley
Papers
1
Total Citations
6
H-Index
1
About
Joshua Riley is a researcher at the forefront of safe and reliable artificial intelligence, with a primary focus on deep multi-agent reinforcement learning (MARL) for robotic systems. His most cited work, "Assured Deep Multi-Agent Reinforcement Learning for Safe Robotic Systems" (2022), addresses a critical challenge in deploying autonomous agents in real-world environments: guaranteeing safety while maintaining performance. Riley’s contributions center on developing formal verification methods and constraint-aware learning algorithms that allow multiple robots to coordinate without compromising safety—a breakthrough for applications in autonomous driving, warehouse logistics, and search-and-rescue operations. Though his career is still early, his work has already garnered 6 citations, signaling growing recognition in the robotics and AI safety communities. Riley’s research bridges the gap between theoretical guarantees and practical deployment, making him a rising voice in the push toward trustworthy autonomous systems. His achievements highlight a commitment to not just advancing AI capabilities, but ensuring they are robust enough for high-stakes, human-centric environments.
Research Focus
Key Achievements
Top Papers
- 1Assured Deep Multi-Agent Reinforcement Learning for Safe Robotic Systems6 citations · 2022