About

Tianhe Yu is a PhD student at Stanford University and a Student Researcher at Google Brain, with a keen interest in machine learning and robotics. He specializes in deep reinforcement learning, offline reinforcement learning, multi-task and meta-learning, and their applications to robotics. Tianhe has a website (https://cs.stanford.edu/~tianheyu) that showcases his work and research interests. Currently, Tianhe works at Google Brain team as a Student Researcher, collaborating with Dr. Karol Hausman and Yevgen Chebotar on data sharing strategies for multi-task offline RL and applications to real-world tasks. He has recently published a paper at NeurIPS 2021 on this topic. Tianhe has previously worked as a Research Intern at Google Brain team, where he worked on multi-task RL on temporally-extended tasks. He has also worked as a Research Assistant at Stanford University, where he collaborated with Dr. Karol Hausman and Yevgen Chebotar on data sharing strategies for multi-task offline RL and applications to real-world tasks. Tianhe holds a Doctor of Philosophy - PhD degree in Computer Science from Stanford University, which he expects to complete in December 2022. He earned his Bachelor's Degree in Applied Mathematics, Statistics, Computer Science from the University of California, Berkeley in 2018. Tianhe is a Research Scientist with a strong background in Reinforcement Learning and Machine Learning. He has 0.43 years of relevant experience in the field. Tianhe is passionate about contributing to the development of intelligent systems that can improve our lives and is always looking for new challenges to tackle.