Anjun Chen

Papers

Total Citations

H-Index

About

Anjun Chen is a rising researcher at the forefront of robotic learning and multi-agent systems, whose work bridges the critical gap between simulation and real-world deployment. Chen’s primary research areas include visual representation learning for robotic manipulation and multi-agent reinforcement learning (MARL) for exploration tasks. In their notable 2024 work, *InterRep*, Chen introduced a novel visual interaction representation that enhances robotic grasping by extracting richer features from pre-trained vision models—a contribution that addresses the underexplored challenge of representation quality in motor control. This paper has already garnered 4 citations, signaling early impact in the field. Complementing this, Chen developed *MAexp*, a generic platform designed to tackle the persistent sim-to-real gap in MARL-based exploration. By improving sampling efficiency and algorithmic diversity, this work provides a robust foundation for scalable multi-robot coordination. With both papers published in 2024, Chen is establishing a reputation for practical, platform-level contributions that empower other researchers. Their focus on bridging theoretical advances with deployable solutions marks them as a promising voice in modern robotics and embodied AI.