Chenliang Li
Papers
1
Total Citations
4
H-Index
1
About
Chenliang Li is a rising researcher in artificial intelligence, with a primary focus on inverse reinforcement learning (IRL) and sequential decision-making. His most notable contribution is the development of the first finite-time analysis for maximum-likelihood IRL, providing rigorous theoretical guarantees for recovering reward functions from expert demonstrations. This work, published in 2022, addresses a fundamental gap in the field—previously, IRL algorithms lacked formal convergence guarantees, relying instead on heuristic or asymptotic arguments. Li's analysis shows that under certain conditions, the maximum-likelihood approach can provably recover the true reward with high probability in a polynomial number of samples. Beyond this core contribution, his research bridges theory and practice, aiming to make IRL more reliable for applications in robotics, autonomous systems, and human-robot interaction. While his citation count is still growing, the foundational nature of his work positions him as a key voice in the theoretical foundations of learning from demonstration. Li's commitment to rigorous, provable methods marks him as a researcher to watch in the evolving landscape of AI and machine learning.
Research Focus
Key Achievements
Top Papers
- 1