Zhang-Wei Hong
Staff Research Member
Categories
Zhang-Wei Hong is a staff research member with IBM Research. His research focuses on advancing reinforcement learning (RL) methods to overcome the challenges of applying RL to computational discovery problems. Discovery problems span a range of applications, from identifying materials that optimize power density in science to designing robot controllers for complex tasks. These problems involve finding solutions that optimize specific objectives using interaction data from systems with unknown dynamics in black-box settings. Hong believes RL is particularly well-suited for solving discovery problems because it learns through interaction, akin to how humans discover new knowledge through trial and error. However, existing RL methods face critical challenges that limit their effectiveness for discovery, like limited learning signals and lack of diversity.
Hong earned a PhD in electrical engineering and computer science from MIT. He completed both his BS and MS degrees at National Tsing Hua University.
Selected Publications
- Mahankali, S. V., Hong, Z‑W., Sekhari, A., Rakhlin, A., & Agrawal, P. (2024). Random Latent Exploration for Deep Reinforcement Learning. Proceedings of the 41st International Conference on Machine Learning (Vol. 235, pp. 34219–34252). PMLR.
- Hong, Z.‑W., Shenfeld, I., Wang, T.‑H., Chuang, Y.‑S., Pareja, A., Glass, J. R., Srivastava, A., & Agrawal, P. (2024). Curiosity‑driven red‑teaming for large language models. In Proceedings of the International Conference on Learning Representations (ICLR).
- Mahankali, S., Lee, C.-C., Margolis, G. B., Hong, Z.-W., & Agrawal, P. (2024). Maximizing quadruped velocity by minimizing energy. In Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA) (pp. 12825–12831).
Media
- April 10, 2024: MIT News, A faster, better way to prevent an AI chatbot from giving toxic responses
- May 31, 2023: MIT News, A more effective way to train machines for uncertain, real-world situations
- November 10, 2022: MIT News, Ensuring AI works with the right dose of curiosity