Weichao Mao
Papers
2
Total Citations
9
H-Index
2
About
Weichao Mao is a researcher advancing the frontiers of reinforcement learning (RL) in complex, real-world settings. His work primarily targets two challenging domains: planning in continuous spaces and decentralized multi-agent cooperation. In his influential paper "POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis" (2020, 6 citations), Mao tackled a critical gap by extending the power of Monte-Carlo Tree Search (MCTS) from finite to continuous state-action spaces. This work provides rigorous theoretical guarantees, offering a principled framework for planning in high-dimensional environments where traditional methods struggle. Further expanding the scope of RL, his research on "Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration" (2021, 3 citations) addresses the fundamental challenge of coordination among agents with aligned objectives, such as in multi-robot navigation. By focusing on exploration in a decentralized setting, Mao’s contributions are paving the way for more robust and scalable solutions in cyber-physical systems and autonomous teams. His work stands out for its strong theoretical foundations, providing non-asymptotic analysis that bridges the gap between theory and practical deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2