Shagun Sodhani

research

∙ 02/14/2022

Robust Policy Learning over Multiple Uncertainty Sets

Reinforcement learning (RL) agents need to be robust to variations in sa...

Annie Xie, et al. ∙

research

∙ 10/13/2021

Block Contextual MDPs for Continual Learning

In reinforcement learning (RL), when defining a Markov Decision Process ...

Shagun Sodhani, et al. ∙

research

∙ 02/11/2021

Multi-Task Reinforcement Learning with Context-based Representations

The benefit of multi-task learning over single-task learning relies on t...

Shagun Sodhani, et al. ∙

research

∙ 12/23/2020

IIRC: Incremental Implicitly-Refined Classification

We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)"...

Mohamed Abdelsalam, et al. ∙

research

∙ 10/06/2020

A Closer Look at Codistillation for Distributed Training

Codistillation has been proposed as a mechanism to share knowledge among...

Shagun Sodhani, et al. ∙

research

∙ 07/21/2020

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

This report documents ideas for improving the field of machine learning,...

Shagun Sodhani, et al. ∙

research

∙ 07/14/2020

Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Multi-task reinforcement learning is a rich paradigm where information f...

Amy Zhang, et al. ∙

research

∙ 04/15/2020

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

With the recent wave of progress in artificial intelligence (AI) has com...

Miles Brundage, et al. ∙

research

∙ 03/14/2020

Evaluating Logical Generalization in Graph Neural Networks

Recent research has highlighted the role of relational inductive biases ...

Koustuv Sinha, et al. ∙

research

∙ 03/12/2020

Invariant Causal Prediction for Block MDPs

Generalization across environments is critical to the successful applica...

Amy Zhang, et al. ∙

research

∙ 09/24/2019

Recurrent Independent Mechanisms

Learning modular structures which reflect the dynamics of the environmen...

Anirudh Goyal, et al. ∙

research

∙ 08/16/2019

CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text

The recent success of natural language understanding (NLU) systems has b...

Koustuv Sinha, et al. ∙

research

∙ 06/25/2019

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives

Reinforcement learning agents that operate in diverse and complex enviro...

Anirudh Goyal, et al. ∙

research

∙ 06/11/2019

Learning Powerful Policies by Using Consistent Dynamics Model

Model-based Reinforcement Learning approaches have the promise of being ...

Shagun Sodhani, et al. ∙

research

∙ 11/26/2018

Environments for Lifelong Reinforcement Learning

To achieve general artificial intelligence, reinforcement learning (RL) ...

Khimya Khetarpal, et al. ∙

research

∙ 11/16/2018

On Training Recurrent Neural Networks for Lifelong Learning

Capacity saturation and catastrophic forgetting are the central challeng...

Shagun Sodhani, et al. ∙

research

∙ 11/07/2018

Compositional Language Understanding with Text-based Relational Reasoning

Neural networks for natural language reasoning have largely focused on e...

Koustuv Sinha, et al. ∙

research

∙ 10/21/2018

Spatial Co-location Pattern Mining - A new perspective using Graph Database

Spatial co-location pattern mining refers to the task of discovering the...

Sanket Vaibhav Mehta, et al. ∙

research

∙ 05/28/2018

Memory Augmented Self-Play

Self-play is an unsupervised training procedure which enables the reinfo...

Shagun Sodhani, et al. ∙

research

∙ 05/21/2018

Reproducibility Report for "Learning To Count Objects In Natural Images For Visual Question Answering"

This is the reproducibility report for the paper "Learning To Count Obje...

Shagun Sodhani, et al. ∙

research

∙ 09/24/2017

Survey of Recent Advances in Visual Question Answering

Visual Question Answering (VQA) presents a unique challenge as it requir...

Supriya Pandhre, et al. ∙

research

∙ 09/17/2017

Reinforcement Learning Based Conversational Search Assistant

In this work, we develop an end-to-end Reinforcement Learning based arch...

Milan Aggarwal, et al. ∙

research

∙ 12/13/2015

Stack Exchange Tagger

The goal of our project is to develop an accurate tagger for questions p...

Sanket Mehta, et al. ∙

Shagun Sodhani

Featured Co-authors

Yoshua Bengio

Sergey Levine

Bernhard Schölkopf

Chelsea Finn

Doina Precup

Joelle Pineau

Jian Tang

Yarin Gal

Adrian Weller

Anirudh Goyal

Marta Kwiatkowska

Robust Policy Learning over Multiple Uncertainty Sets

Block Contextual MDPs for Continual Learning

Multi-Task Reinforcement Learning with Context-based Representations

IIRC: Incremental Implicitly-Refined Classification

A Closer Look at Codistillation for Distributed Training

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

Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

Evaluating Logical Generalization in Graph Neural Networks

Invariant Causal Prediction for Block MDPs

Recurrent Independent Mechanisms

CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives

Learning Powerful Policies by Using Consistent Dynamics Model

Environments for Lifelong Reinforcement Learning

On Training Recurrent Neural Networks for Lifelong Learning

Compositional Language Understanding with Text-based Relational Reasoning

Spatial Co-location Pattern Mining - A new perspective using Graph Database

Memory Augmented Self-Play

Reproducibility Report for "Learning To Count Objects In Natural Images For Visual Question Answering"

Survey of Recent Advances in Visual Question Answering

Reinforcement Learning Based Conversational Search Assistant

Stack Exchange Tagger