Jiankang Ren

About

Jiankang Ren is a researcher in artificial intelligence, specializing in reinforcement learning and multiagent robotic control. His work focuses on bridging the gap between human guidance and autonomous decision-making, particularly in complex, decentralized environments. Ren’s most cited paper, "Adaptively Shaping Reinforcement Learning Agents via Human Reward" (2018, 7 citations), introduces a novel framework that allows human trainers to dynamically shape agent behavior through real-time reward signals, enhancing learning efficiency and safety. This contribution is pivotal for applications where human oversight is critical, such as assistive robotics and interactive AI. In his second notable work, "Decentralized Multiagent Reinforcement Learning for Efficient Robotic Control by Coordination Graphs" (2018, 2 citations), Ren advances coordination among multiple robots by leveraging graph-based structures, enabling scalable and robust control in tasks like warehouse automation or search-and-rescue missions. Though early in his career, Ren’s research has already influenced the development of human-in-the-loop learning systems and cooperative multiagent strategies, laying groundwork for more intuitive and reliable AI systems. His work underscores a commitment to making reinforcement learning more adaptable and collaborative.

Research Focus

Key Achievements

Top Papers

1. 1
   Adaptively Shaping Reinforcement Learning Agents via Human Reward

   7 citations · 2018
2. 2
   Decentralized Multiagent Reinforcement Learning for Efficient Robotic Control by Coordination Graphs

   2 citations · 2018

Key Collaborators

Contact & Links