Baoqian Wang

Papers

Total Citations

H-Index

About

Baoqian Wang is a researcher advancing the frontiers of distributed machine learning, with a primary focus on multi-agent reinforcement learning (MARL) and the reliability of large-scale computing systems. His most-cited work, "Coding for Distributed Multi-Agent Reinforcement Learning" (2021), addresses a critical bottleneck in synchronous distributed learning: the straggler effect, where slow or failed compute nodes delay the entire system. By introducing coding-theoretic techniques, Wang’s research provides a novel framework to mitigate these disturbances, enabling more robust and efficient MARL in real-world deployments. Though early in his career, with this paper garnering 3 citations, his contribution is notable for bridging information theory and reinforcement learning—a cross-disciplinary approach that holds promise for scalable, fault-tolerant AI systems. Wang’s work is particularly relevant for applications in autonomous driving, robotics, and networked systems, where distributed agents must learn cooperatively under unpredictable hardware conditions. As distributed learning grows in complexity, his insights into coding for straggler resilience position him as an emerging voice in making MARL both practical and resilient.