Yuchang Wu

Papers

Total Citations

H-Index

About

Yuchang Wu is a rising researcher in artificial intelligence, with a core focus on multi-objective reinforcement learning (MORL) and decision-making under conflicting criteria. Wu’s most notable contribution is the development of Pareto set learning for MORL, a framework that enables agents to efficiently approximate the entire set of optimal trade-off solutions—rather than a single policy—in complex environments like video games, navigation, and robotics. This work, published in 2025 and already garnering 5 citations, addresses a critical gap in traditional RL by allowing systems to balance multiple, often competing objectives simultaneously. Wu’s approach leverages the power of deep learning to map preference vectors directly to Pareto-optimal policies, significantly reducing computational overhead compared to prior methods. By advancing the theoretical and practical foundations of multi-objective decision-making, Wu is helping to make RL more adaptable to real-world scenarios where trade-offs are inevitable. As an early-career scholar, Wu’s work signals a promising trajectory in making AI systems more aligned with complex human values and operational constraints.