Kai-Chen Huang @ LAMDA, NJU-AI

M.Sc. Student, LAMDA Group
School of Artificial Intelligence
National Key Laboratory for Novel Software Technology
Nanjing University, Nanjing 210023, China
Supervisor: De-Chuan Zhan(詹德川)
Laboratory: Yifu Building, Xianlin Campus of Nanjing University
Email: huangkc@lamda.nju.edu.cn

• Kaichen Huang*, Shenghua Wan*, Minghao Shao, Shuai Feng, Le Gan, De-Chuan Zhan. Leveraging Separated World Model for Exploration in Visually Distracted Environments. In: Advances in Neural Information Processing Systems 37 (NeurIPS-2024), Vancouver, Canada, 2024. [Paper] [Code]

We propose a bi-level optimization framework named Separation-assisted eXplorer (SeeX). In the inner optimization, SeeX trains a separated world model to extract exogenous and endogenous information, minimizing uncertainty to ensure task relevance. In the outer optimization, it learns a policy on imaginary trajectories generated within the endogenous state space to maximize task-relevant uncertainty.

• Yihan Liu, Kaichen Huang, Yechao Bai. An Error Analysis Method for Externally Measured Data. Published in the Chinese core journal Measurement and Control Technology, Vol. 42, No. 2, 2023. [Paper] (Completed at undergraduate)

We propose a method for analyzing external ballistic measurement errors caused by various conditions, which result in unobservable random errors and latent systematic errors. Using Intrinsic Mode Function (IMF) energy inflection points, this method categorizes IMFs into high-frequency errors, mixed information, and useful information, effectively compensating for systematic errors and improving positioning accuracy.

• Kaichen Huang*, Hai-Hang Sun*, Shenghua Wan, Minghao Shao, Shuai Feng, Le Gan, De-Chuan Zhan. LTI-Mimic: Learning from Demonstrations with Linear Time-Invariant Noise via Dual-Discriminator. [Paper] [Code]

We focus on the problem of Learning from Noisy Demonstrations (LND), where the imitator is required to learn from data with noise that often occurs during the processes of data collection or transmission. We propose LTI-Mimic, which designs two discriminators to distinguish the noise level and expertise level of data, facilitating a feature encoder to learn task-related but domain-agnostic representations.

• Kaichen Huang*, Minghao Shao*, Shenghua Wan, Hai-Hang Sun, Shuai Feng, Le Gan, De-Chuan Zhan. SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring. [Paper] [Code]

We introduce active sensoring in the visual IL setting and propose a model-based SENSory imitatOR (SENSOR) to automatically change the agent's perspective to match the expert's. SENSOR jointly learns a world model to capture the dynamics of latent states, a sensor policy to control the camera, and a motor policy to control the agent.