Timezone: »

 
Spotlight
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Jim Fan · Guanzhi Wang · De-An Huang · Zhiding Yu · Li Fei-Fei · Yuke Zhu · Anima Anandkumar

Tue Jul 20 06:25 PM -- 06:30 PM (PDT) @
in Reinforcement Learning 6 »

Generalization has been a long-standing challenge for reinforcement learning (RL). Visual RL, in particular, can be easily distracted by irrelevant factors in high-dimensional observation space. In this work, we consider robust policy learning which targets zero-shot generalization to unseen visual environments with large distributional shift. We propose SECANT, a novel self-expert cloning technique that leverages image augmentation in two stages to decouple robust representation learning from policy optimization. Specifically, an expert policy is first trained by RL from scratch with weak augmentations. A student network then learns to mimic the expert policy by supervised learning with strong augmentations, making its representation more robust against visual variations compared to the expert. Extensive experiments demonstrate that SECANT significantly advances the state of the art in zero-shot generalization across 4 challenging domains. Our average reward improvements over prior SOTAs are: DeepMind Control (+26.5%), robotic manipulation (+337.8%), vision-based autonomous driving (+47.7%), and indoor object navigation (+15.8%). Code release and video are available at https://linxifan.github.io/secant-site/.

Keywords: Reinforcement Learning and Planning · Deep RL

Author Information

Jim Fan (Stanford University)
Guanzhi Wang (Stanford University)
De-An Huang (NVIDIA)
Zhiding Yu (NVIDIA)

Zhiding Yu is a Senior Research Scientist at NVIDIA. Before joining NVIDIA in 2018, he received Ph.D. in ECE from Carnegie Mellon University in 2017, and M.Phil. in ECE from The Hong Kong University of Science and Technology in 2012. His research interests mainly focus on deep representation learning, weakly/self-supervised learning, transfer learning and deep structured prediction, with their applications to vision and robotics problems.

Li Fei-Fei (Stanford University)
Yuke Zhu (University of Texas - Austin)
Anima Anandkumar (Caltech and NVIDIA)

Anima Anandkumar is a Bren Professor at Caltech and Director of ML Research at NVIDIA. She was previously a Principal Scientist at Amazon Web Services. She is passionate about designing principled AI algorithms and applying them to interdisciplinary domains. She has received several honors such as the IEEE fellowship, Alfred. P. Sloan Fellowship, NSF Career Award, Young investigator awards from DoD, Venturebeat’s “women in AI” award, NYTimes GoodTech award, and Faculty Fellowships from Microsoft, Google, Facebook, and Adobe. She is part of the World Economic Forum's Expert Network. She has appeared in the PBS Frontline documentary on the “Amazon empire” and has given keynotes in many forums such as the TEDx, KDD, ICLR, and ACM. Anima received her BTech from Indian Institute of Technology Madras, her PhD from Cornell University, and did her postdoctoral research at MIT and assistant professorship at University of California Irvine.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors