Weihao Tan

About

Weihao Tan is a rising researcher in artificial intelligence, whose work focuses on advancing multi-agent reinforcement learning (MARL) for real-world robotic systems. His most-cited paper, “Asynchronous Multi-Agent Deep Reinforcement Learning under Partial Observability” (2025, 5 citations), tackles a critical limitation of existing MARL methods: the unrealistic assumption that agents act in perfect synchrony. By introducing a framework that allows agents to operate asynchronously under partial observability, Tan addresses the challenges of long-horizon, real-world multi-robot tasks where coordination delays and incomplete information are inevitable. This contribution bridges the gap between theoretical MARL and practical deployment, offering a more scalable and robust approach for applications like autonomous fleets and distributed sensor networks. Though early in his career, Tan’s work has already garnered attention for its pragmatic focus on real-world constraints, positioning him as a promising voice in the intersection of reinforcement learning and robotics. His research underscores a commitment to making AI systems not just intelligent, but also operationally viable in complex, dynamic environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Asynchronous multi-agent deep reinforcement learning under partial observability

   5 citations · 2025

Key Collaborators

Contact & Links