Rae Chan Jeong

Title: Rae Chan Jeong: Innovator in Reinforcement Learning

Introduction

Rae Chan Jeong is a prominent inventor based in New York, California. She has made significant contributions to the field of reinforcement learning, particularly in the context of continuous control systems. Her innovative work has led to the development of a patented method that enhances the efficiency and effectiveness of policy neural networks.

Latest Patents

Rae Chan Jeong holds a patent titled "Robust reinforcement learning for continuous control with model misspecification." This patent encompasses methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a policy neural network with specific policy parameters. One of the key methods involves sampling a mini-batch of observation-action-reward tuples generated from the interactions of a first agent with a first environment. The process includes determining updates to the Q network parameters by minimizing a robust entropy-regularized temporal difference (TD) error, which accounts for potential perturbations in the states of the first environment. Additionally, the Q-value neural network is utilized to update the policy network parameters based on the sampled mini-batch.

Career Highlights

Rae Chan Jeong has established herself as a leading figure in her field through her innovative research and development efforts. Her work has not only advanced the understanding of reinforcement learning but has also provided practical applications that can be utilized in various industries.

Collaborations

Rae has collaborated with notable professionals in her field, including Daniel J. Mankowitz and Nir Levine. These collaborations have further enriched her research and contributed to the advancement of reinforcement learning technologies.

Conclusion

Rae Chan Jeong's contributions to the field of reinforcement learning exemplify her dedication to innovation and excellence. Her patented methods are paving the way for future advancements in continuous control systems.