Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods



Yi Wan , Ali Rahimi-Kalahroudi , Janarthanan Rajendran , Ida Momennejad , Sarath Chandar , Harm van Seijen


   Access Paper or Ask Questions

Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers



Amir Ardalan Kalantari , Mohammad Amini , Sarath Chandar , Doina Precup


   Access Paper or Ask Questions

An Empirical Investigation of the Role of Pre-training in Lifelong Learning



Sanket Vaibhav Mehta , Darshan Patil , Sarath Chandar , Emma Strubell

* 30 pages 

   Access Paper or Ask Questions

Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers



Gabriele Prato , Simon Guiroy , Ethan Caballero , Irina Rish , Sarath Chandar


   Access Paper or Ask Questions

Post-hoc Interpretability for Neural NLP: A Survey



Andreas Madsen , Siva Reddy , Sarath Chandar


   Access Paper or Ask Questions

Demystifying Neural Language Models' Insensitivity to Word-Order



Louis Clouatre , Prasanna Parthasarathi , Amal Zouaq , Sarath Chandar

* 11 pages, 13 figure + appendix 

   Access Paper or Ask Questions

Memory Augmented Optimizers for Deep Learning



Paul-Aymeric McRae , Prasanna Parthasarathi , Mahmoud Assran , Sarath Chandar

* 24 Pages. Currently under review 

   Access Paper or Ask Questions

Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?



Prasanna Parthasarathi , Joelle Pineau , Sarath Chandar

* Accepted at SIGDial 2021. arXiv admin note: substantial text overlap with arXiv:2008.10427 

   Access Paper or Ask Questions

A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss



Prasanna Parthasarathi , Mohamed Abdelsalam , Joelle Pineau , Sarath Chandar

* Accepted at SIGDial 2021 

   Access Paper or Ask Questions

1
2
3
4
5
>>