activity
20172022
most citedToward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

219 citations · 258 across the 8 of their papers we have counts for

collaborators

21 papers

cs.LG20221 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…

cs.LG20213 cited

Block Contextual MDPs for Continual Learning

Shagun Sodhani, Franziska Meier, Joelle Pineau +1

In reinforcement learning (RL), when defining a Markov Decision Process (MDP), the environment dynamics is implicitly assumed to be stationary. This assumption of stationarity, whi…

cs.LG2021

Multi-Task Reinforcement Learning with Context-based Representations

Shagun Sodhani, Amy Zhang, Joelle Pineau

The benefit of multi-task learning over single-task learning relies on the ability to use relations across tasks to improve performance on any single task. While sharing representa…

cs.CV2021

IIRC: Incremental Implicitly-Refined Classification

Mohamed Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani +1

We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)" setup, an extension to the class incremental learning setup where the incoming batches of classes have two…

cs.LG2020

A Closer Look at Codistillation for Distributed Training

Shagun Sodhani, Olivier Delalleau, Mahmoud Assran +3

Codistillation has been proposed as a mechanism to share knowledge among concurrently trained models by encouraging them to represent the same function through an auxiliary loss. T…

cs.CY2020

Ideas for Improving the Field of Machine Learning: Summarizing Discussion from the NeurIPS 2019 Retrospectives Workshop

Shagun Sodhani, Mayoore S. Jaiswal, Lauren Baker +5

This report documents ideas for improving the field of machine learning, which arose from discussions at the ML Retrospectives workshop at NeurIPS 2019. The goal of the report is t…