Microsoft AI
Haiper
University of British Columbia
University of Oxford
Shimon WhitesonResearch Director · Google DeepMindResearcher↗
Researcher
Ziyu Wang
Google DeepMindResearch Scientist
Wang co-created the dueling network architecture, which helped reinforcement-learning agents distinguish the value of a situation from the value of individual actions.[1] His later work applies learning from demonstrations and experience to games, robotics, and general-purpose AI agents.
Career & education
Current roleGoogle DeepMindMar 2026-presentResearch Scientist
Google DeepMindMar 2026-presentPreviously
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations35,826As of Oct 20, '26
citations+2,128Since last snapshot, Jun 15, '26
References
- Dueling Network Architectures for Deep Reinforcement Learningproceedings.mlr.press
Wang is first author of the 2016 ICML paper introducing separate estimators for state value and action advantage.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 8, 2026 · Checked for accuracy and new information.
