Building a Subspace of Policies for Scalable Continual Learning

International Conference on Learning Representations (ICLR)


The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to learn a large number of diverse behaviors, or growing-size models that scale poorly with the number of tasks. In this work, we aim to strike a better balance between an agent’s size and performance by designing a method that grows adaptively depending on the task sequence. We introduce Continual Subspace of Policies (CSP), a new approach that incrementally builds a subspace of policies for training a reinforcement learning agent on a sequence of tasks. The subspace’s high expressivity allows CSP to perform well for many different tasks while growing sublinearly with the number of tasks. Our method does not suffer from forgetting and displays positive transfer to new tasks. CSP outperforms a number of popular baselines on a wide range of scenarios from two challenging domains, Brax (locomotion) and Continual World (manipulation). Interactive visualizations of the subspace can be found at csp. Code is available here.

Latest Publications

A Practical Stereo Depth System for Smart Glasses

Jialiang Wang, Daniel Scharstein, Akash Bapat, Kevin Blackburn-Matzen Matthew Yu, Jonathan Lehman, Suhib Alsisan, Yanghan Wang, Sam Tsai, Jan-Michael Frahm, Zijian He, Peter Vajda, Michael Cohen, Matt Uyttendaele

CVPR - 2023

Presto: A Decade of SQL Analytics at Meta

Yutian James Sun, Tim Meehan, Rebecca Schlussel, Wenlei Xie, Masha Basmanova, Orri Erling, Andrii Rosa, Shixuan Fan, Rongrong Zhong, Arun Thirupathi, Nikhil Collooru, Ke Wang, Sameer Agarwal, Arjun Gupta, Dionysios Logothetis, Kostas Xirogiannopoulos, Bin Fan, Amit Dutta, Varun Gajjala, Rohit Jain, Ajay Palakuzhy, Prithvi Pandian, Sergey Pershin, Abhisek Saikia, Pranjal Shankhdhar, Neerad Somanchi, Swapnil Tailor, Jialiang Tan, Sreeni Viswanadha, Zac Wen, Deepak Majeti, Aditi Pandit, Biswapesh Chattopadhyay

SIGMOD - 2023