Annie Xie

I am a final-year PhD student in CS at Stanford University, advised by Chelsea Finn. My research was previously supported by the NSF Graduate Research Fellowship.

Prior to Stanford, I graduated from UC Berkeley, where I studied EECS and worked with Sergey Levine in the Berkeley Artificial Intelligence Research (BAIR) Lab.

Email  /  CV  /  Google Scholar

Research
Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation
Annie Xie*, Lisa Lee*, Ted Xiao, Chelsea Finn
International Conference on Robotics and Automation (ICRA), 2024
[arxiv][webpage]
Supervised Pretraining Can Learn In-Context Reinforcement Learning
Jonathan N. Lee*, Annie Xie*, Aldo Pacchiano, Yash Chandak, Chelsea Finn, Ofir Nachum, Emma Brunskill
Conference on Neural Information Processing Systems (NeurIPS), 2023 (Spotlight)
[arxiv]
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
Annie Xie*, Fahim Tajwar*, Archit Sharma*, Chelsea Finn
Conference on Neural Information Processing Systems (NeurIPS), 2022
[arxiv][webpage]
Lifelong Robotic Reinforcement Learning by Retaining Experiences
Annie Xie, Chelsea Finn
Conference on Lifelong Learning Agents (CoLLAs), 2022
Robot Learning Workshop at NeurIPS, 2021 (Best Paper Award)
[arxiv][webpage]
Robust Policy Learning over Multiple Uncertainy Sets
Annie Xie, Shagun Sodhani, Chelsea Finn, Joelle Pineau, Amy Zhang
International Conference on Machine Learning (ICML), 2022
[arxiv][webpage]
Influencing Towards Stable Multi-Agent Interactions
Woodrow Zhouyuan Wang, Andy Shih, Annie Xie, Dorsa Sadigh
Conference on Robot Learning (CoRL), 2021 (Oral Presentation)
[arxiv][webpage]
Deep Reinforcement Learning amidst Lifelong Non-Stationarity
Annie Xie, James Harrison, Chelsea Finn
International Conference on Machine Learning (ICML), 2021
Lifelong Learning Workshop at ICML, 2020 (Best Paper Award)
[arxiv] [webpage]
Learning Latent Representations to Influence Multi-Agent Interaction
Annie Xie, Dylan P. Losey, Ryan Tolsma, Chelsea Finn, Dorsa Sadigh
Conference on Robot Learning (CoRL), 2020 (Best Paper Award)
[arxiv] [webpage] [blog post]
Learning Predictive Models From Observation and Interaction
Karl Schmeckpeper, Annie Xie, Oleh Rybkin, Stephen Tian, Kostas Daniilidis, Sergey Levine, Chelsea Finn
European Conference on Computer Vision (ECCV), 2020
[arxiv] [webpage]
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight
Annie Xie, Frederik Ebert, Sergey Levine, Chelsea Finn
Robotics: Science and Systems (RSS), 2019
[arxiv] [webpage] [blog post]
Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
Frederik Ebert, Chelsea Finn, Sudeep Dasari, Annie Xie, Alex Lee, Sergey Levine
2018
[arxiv] [webpage] [blog post]
Few-Shot Goal Inference for Visuomotor Learning and Planning
Annie Xie, Avi Singh, Sergey Levine, Chelsea Finn
Conference on Robot Learning (CoRL), 2018
[arxiv] [webpage]
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
Tianhe Yu, Chelsea Finn, Annie Xie, Sudeep Dasari, Tianhao Zhang, Pieter Abbeel, Sergey Levine
Robotics: Science and Systems (RSS), 2018
[arxiv] [webpage]

website template