Jiacheng Zhou

Papers

Total Citations

H-Index

About

Jiacheng Zhou is a rising researcher at the forefront of multi-agent reinforcement learning (MARL), with a focus on bridging the critical sim-to-real gap in robotic exploration. His most-cited work, "MAexp: A Generic Platform for RL-based Multi-Agent Exploration" (2024, 4 citations), tackles the fundamental challenges of scene quantization and action discretization that plague existing simulation platforms. Zhou's major contribution lies in designing a more efficient and diverse sampling framework that supports a wide range of MARL algorithms, enabling more realistic and scalable multi-agent coordination. While still early in his career, his work addresses a pressing bottleneck in deploying RL-trained policies to physical robots. By improving the fidelity and flexibility of simulation environments, Zhou is laying the groundwork for more robust autonomous exploration in unknown terrains—critical for applications in search-and-rescue, planetary exploration, and environmental monitoring. His research stands out for its practical orientation, directly targeting the inefficiencies that have long hindered real-world MARL deployment. As the field increasingly demands sim-to-real transfer, Zhou's platform-oriented approach positions him as a key contributor to the next generation of intelligent, collaborative robotic systems.