activity
20172025
most citedToward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

219 citations · 336 across the 21 of their papers we have counts for

collaborators
Showing cs.LGShow all

18 papers · 1 filter

cs.LG2023

Harnessing small projectors and multiple views for efficient vision pretraining

Kumar Krishna Agrawal, Arna Ghosh, Shagun Sodhani +2

Recent progress in self-supervised (SSL) visual representation learning has led to the development of several different proposed frameworks that rely on augmentations of images but…

cs.LG2023★ 16 cited

TorchRL: A data-driven decision-making library for PyTorch

Albert Bou, Matteo Bettini, Sebastian Dittert +5

PyTorch has ascended as a premier machine learning framework, yet it lacks a native and comprehensive library for decision and control tasks suitable for large development teams de…

cs.LG2023★ 5 cited

When should we prefer Decision Transformers for Offline Reinforcement Learning?

Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard +2

Offline reinforcement learning (RL) allows agents to learn effective, return-maximizing policies from a static dataset. Three popular algorithms for offline RL are Conservative Q-L…

cs.LG2022★ 12 cited

The Neural Race Reduction: Dynamics of Abstraction in Gated Networks

Andrew M. Saxe, Shagun Sodhani, Sam Lewallen

Our theoretical understanding of deep learning has not kept pace with its empirical success. While network architecture is known to be critical, we do not yet understand its effect…

cs.LG2022★ 4 cited

An Introduction to Lifelong Supervised Learning

Shagun Sodhani, Mojtaba Faramarzi, Sanket Vaibhav Mehta +4

This primer is an attempt to provide a detailed summary of the different facets of lifelong learning. We start with Chapter 2 which provides a high-level overview of lifelong learn…

cs.LG2022★ 1 cited

Robust Policy Learning over Multiple Uncertainty Sets

Annie Xie, Shagun Sodhani, Chelsea Finn +2

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from on…