Weichao Zhou

I am a Ph.D. student at the Department of Electrical and Computer Engineering at Boston University. My research interests span reinforcement learning (RL), robust machine learning, and formal methods. My research projects are focused on using formal specifications and data-driven approaches to learn reward functions for reinforcement learning. I am also working on the robustness analysis of neural network control systems (NNCSs) and backdoor attack detection on neural networks in various applications, including computer vision and reinforcement learning.

Here is my research statement.

Contact: zwc662@bu.edu

Updates

[2024/02/21] New preprint of “Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning" is available.

[2023/09/28] New preprint of “PAGAR: Taming Reward Misalignment in Inverse Reinforcement Learning-Based Imitation Learning with Protagonist Antagonist Guided Adversarial Reward” is available. [code]

[2023/010/20] Our workshop paper “Universal Trojan Signatures in Reinforcement Learning” has been accepted by NeurIPS 2023 BUGS !!

[2023/010/20] Our submission “POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems” has been accepted by TCAD 2023 !!

Select Papers