基本信息
浏览量:188
职业迁徙
个人简介
My research goal is to add *wisdom* and *insight* to AI systems, including generative models -- and doing so through value-based reinforcement learning.
I am a researcher, research designer, and problem solver. My main area of focus is reinforcement learning (RL) and sequential reasoning. I have had core contributions in conceiving and execution of several interesting RL projects over the past 14 years, during both my industrial and academic research roles. Such projects include invention of dead-end theory and analysis; dynamical causality; (SOTA) detoxification of Large Language Models through far-sighted reasoning; value mapping in RL; separation of concerns (SoC) in RL; Ms. Pac-Man; RL for dialogue systems; and cognitive control. I also hold five US patents on RL subjects.
On the other side of my brain, I love computational programming and high-quality coding. I have conducted many private computational programming tutorials and consulting sessions.
My research (from various projects) has been highlighted in several popular media outlets including MIT News, Time, BBC, Fortune Magazine, Business Insider, Tech Crunch and many more. In older days, my PhD thesis research (advised by Simon Haykin) featured on the front cover of Proceedings of the IEEE, in addition to be the subject of several invited talks around the globe, including MIT, Oak Ridge National Labs, Salk Institute, RIKEN (Japan), RDC, and UCLA.
I am a researcher, research designer, and problem solver. My main area of focus is reinforcement learning (RL) and sequential reasoning. I have had core contributions in conceiving and execution of several interesting RL projects over the past 14 years, during both my industrial and academic research roles. Such projects include invention of dead-end theory and analysis; dynamical causality; (SOTA) detoxification of Large Language Models through far-sighted reasoning; value mapping in RL; separation of concerns (SoC) in RL; Ms. Pac-Man; RL for dialogue systems; and cognitive control. I also hold five US patents on RL subjects.
On the other side of my brain, I love computational programming and high-quality coding. I have conducted many private computational programming tutorials and consulting sessions.
My research (from various projects) has been highlighted in several popular media outlets including MIT News, Time, BBC, Fortune Magazine, Business Insider, Tech Crunch and many more. In older days, my PhD thesis research (advised by Simon Haykin) featured on the front cover of Proceedings of the IEEE, in addition to be the subject of several invited talks around the globe, including MIT, Oak Ridge National Labs, Salk Institute, RIKEN (Japan), RDC, and UCLA.
研究兴趣
论文共 30 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Scientific Reportsno. 1 (2024): 1-13
ICLR 2023 (2023)
引用2浏览0EI引用
2
0
Conference on Health, Inference, and Learning (CHIL)pp.119-137, (2022)
引用0浏览0EI引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn