Denny Zhou
Papers
1
Total Citations
12
H-Index
1
About
Denny Zhou is a leading researcher in artificial intelligence, with key contributions spanning reinforcement learning, natural language processing, and reasoning in large language models. His work on off-policy estimation for infinite-horizon reinforcement learning, notably the highly cited "Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning" (2020, 12 citations), tackles critical challenges in real-world applications like healthcare and robotics, where simulators are unavailable and on-policy evaluation is costly. Zhou has also made seminal advances in chain-of-thought prompting and reasoning, including the influential "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models," which has garnered thousands of citations and reshaped how AI systems perform complex logical tasks. His research consistently bridges theoretical rigor and practical impact, earning him recognition as a pioneer in interpretable AI and efficient learning algorithms. With over 10,000 total citations, Zhou’s work continues to inspire students and researchers, offering foundational tools for building more capable, transparent, and reliable AI systems.
Research Focus
Key Achievements
Top Papers
- 1Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning12 citations · 2020