Pinqian Dong

About

Pinqian Dong is a rising researcher in artificial intelligence and robotics, with a primary focus on inverse reinforcement learning and imitation learning. Her most impactful work, "Adversarial Inverse Reinforcement Learning With Self-Attention Dynamics Model" (2021), addresses a critical challenge in learning from expert demonstrations: the instability caused by stochastic environments. By integrating a self-attention mechanism into the dynamics model, Dong's approach significantly improves the robustness and sample efficiency of adversarial inverse reinforcement learning (AIRL), enabling more reliable policy learning in complex, real-world scenarios where reward functions are unknown. This paper has garnered 32 citations, reflecting its influence in advancing practical imitation learning. Dong's contributions are particularly valuable for applications in autonomous navigation, robot manipulation, and human-robot interaction, where expert demonstrations are abundant but explicit reward design is impractical. Her work stands out for bridging theoretical advances in attention-based models with the practical demands of reinforcement learning, marking her as a promising voice in the next generation of AI researchers dedicated to making machines learn more naturally from human expertise.

Research Focus

Key Achievements

Top Papers

1. 1
   Adversarial Inverse Reinforcement Learning With Self-Attention Dynamics Model

   32 citations · 2021

Key Collaborators

Contact & Links