Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning
Naoki Yokoyama
Maks Sorokin
Description: NLP Algorithm Engineer
Hi! I’m a NLP algorithm engineer at Alibaba Artificial Intelligence Governance Laboratory ( AAIG ), Alibaba Group, advised by Dr. Longtao Huang . Prior joining Alibaba, I received my M.S. Degree from Georgia Institute of Technology, where I was advised by Prof. Sehoon Ha . I also worked closely with Prof. Dhruv Batra and Prof. Woon-Hong Yeo .
My research interest lies in Deep Reinforcement Learning, Meta Learning, and their applications in CV, NLP and Robotics.
Published with Wowchemy — the free, open source website builder that empowers creators.
Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning
Naoki Yokoyama
Maks Sorokin