About

Jiexin Wang is a researcher whose work lies at the intersection of reinforcement learning, robotics, and bio-inspired control systems. Their primary research areas include modular deep reinforcement learning, policy search algorithms, and robot navigation. Wang’s most notable contribution is the development of a modular deep reinforcement learning framework for robot navigation, which decomposes complex monolithic tasks into parallel sub-goals—a pattern inspired by neural evidence from animal brains. This work, published in 2020, has garnered 60 citations, highlighting its influence in the field. Additionally, Wang has advanced EM-based policy search methods, demonstrating their effectiveness in real-world robotic tasks such as the view-based positioning of a smartphone balancer (41 citations) and the standing and balancing of a two-wheeled smartphone robot. Their 2016 paper on EM-based Policy Hyper Parameter Exploration (EPHE) integrates Policy Gradient with Parameter Exploration and EM-based Reward-Weighted Regression, offering a gradient-free, stable learning approach. Through these contributions, Wang has pushed the boundaries of how robots learn from reward and punishment, making strides toward more adaptive, animal-like learning in autonomous systems.

Research Focus

Key Achievements

3
H-Index
3
Papers
110
Total Citations
37
Avg Citations/Paper
🏆 Most Cited Paper
Modular deep reinforcement learning from reward and punishment for robot navigation
60 citations · 2020
📈 Most Prolific Year: 2020 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Advanced Telecommunications Research Institute International, Okinawa Institute of Science and Technology Graduate University, Kyoto University

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago