Max Robotics — Global Service Robot Directory + US Certification

About

Yupeng Liang is a researcher specializing in multi-agent systems, swarm robotics, and reinforcement learning, with a focus on enabling intelligent collective behaviors in robotic teams. His most impactful work, "Generating collective foraging behavior for robotic swarm using deep reinforcement learning" (2020, 18 citations), introduces a novel framework that leverages deep reinforcement learning to train robotic swarms to autonomously coordinate and execute complex foraging tasks—a foundational challenge in distributed robotics. Building on this, Liang developed a hierarchical training method (2021, 6 citations) that improves scalability and learning efficiency for swarm coordination, addressing key limitations in real-world deployment. More recently, his exploration of multi-agent adversarial environments (2023, 2 citations) combines reinforcement learning with imitation learning to create robust, adaptive agents capable of strategic competition. Liang’s contributions are particularly notable for bridging theoretical reinforcement learning algorithms with practical swarm applications, offering scalable solutions for search-and-rescue, environmental monitoring, and autonomous logistics. His work has been recognized for advancing the frontier of decentralized intelligence, with cumulative citations reflecting growing interest from both robotics and AI communities.