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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Karthik Narasimhan

Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents


Mar 25, 2021
Shunyu Yao, Karthik Narasimhan, Matthew Hausknecht

* NAACL 2021 

  Access Paper or Ask Questions

Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning


Jan 19, 2021
H. J. Austin Wang, Karthik Narasimhan


  Access Paper or Ask Questions

Connecting Context-specific Adaptation in Humans to Meta-learning


Dec 01, 2020
Rachit Dubey, Erin Grant, Michael Luo, Karthik Narasimhan, Thomas Griffiths

* 9 pages 

  Access Paper or Ask Questions

Generating Strategic Dialogue for Negotiation with Theory of Mind


Oct 20, 2020
Runzhe Yang, Jingxiao Chen, Karthik Narasimhan

* 12 pages, 3 figures 

  Access Paper or Ask Questions

Safe Reinforcement Learning with Natural Language Constraints


Oct 11, 2020
Tsung-Yen Yang, Michael Hu, Yinlam Chow, Peter J. Ramadge, Karthik Narasimhan

* The first two authors contributed equally 

  Access Paper or Ask Questions

Projection-Based Constrained Policy Optimization


Oct 07, 2020
Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge

* International Conference on Learning Representations (ICLR) 2020 

  Access Paper or Ask Questions

Keep CALM and Explore: Language Models for Action Generation in Text-based Games


Oct 06, 2020
Shunyu Yao, Rohan Rao, Matthew Hausknecht, Karthik Narasimhan

* EMNLP 2020 

  Access Paper or Ask Questions

Guiding Attention for Self-Supervised Learning with Transformers


Oct 06, 2020
Ameet Deshpande, Karthik Narasimhan

* Accepted to Findings of EMNLP, 2020 

  Access Paper or Ask Questions

Learning Rewards from Linguistic Feedback


Sep 30, 2020
Theodore R. Sumers, Mark K. Ho, Robert D. Hawkins, Karthik Narasimhan, Thomas L. Griffiths

* 9 pages, 4 figures 

  Access Paper or Ask Questions

Towards Unique and Informative Captioning of Images


Sep 08, 2020
Zeyu Wang, Berthy Feng, Karthik Narasimhan, Olga Russakovsky

* ECCV 2020 

  Access Paper or Ask Questions

Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation


Jul 11, 2020
Zhiwei Deng, Karthik Narasimhan, Olga Russakovsky


  Access Paper or Ask Questions

Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies


Jun 20, 2020
Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan, Peter J. Ramadge


  Access Paper or Ask Questions

Universal Adversarial Attacks with Natural Triggers for Text Classification


May 01, 2020
Liwei Song, Xinwei Yu, Hsuan-Tung Peng, Karthik Narasimhan

* code is available at https://github.com/Hsuan-Tung/universal_attack_natural_trigger 

  Access Paper or Ask Questions

Take the Scenic Route: Improving Generalization in Vision-and-Language Navigation


Mar 31, 2020
Felix Yu, Zhiwei Deng, Karthik Narasimhan, Olga Russakovsky

* 4 page short paper 

  Access Paper or Ask Questions

A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation


Aug 21, 2019
Runzhe Yang, Xingyuan Sun, Karthik Narasimhan


  Access Paper or Ask Questions

Calibration, Entropy Rates, and Memory in Language Models


Jun 11, 2019
Mark Braverman, Xinyi Chen, Sham M. Kakade, Karthik Narasimhan, Cyril Zhang, Yi Zhang


  Access Paper or Ask Questions

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning


May 14, 2019
Yilun Du, Karthik Narasimhan

* ICML 2019 

  Access Paper or Ask Questions

Representation Learning for Grounded Spatial Reasoning


Nov 11, 2017
Michael Janner, Karthik Narasimhan, Regina Barzilay

* Accepted to TACL 2017, code: https://github.com/jannerm/spatial-reasoning 

  Access Paper or Ask Questions

Deep Transfer in Reinforcement Learning by Language Grounding


Aug 01, 2017
Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

* 12 pages (incl. references) 

  Access Paper or Ask Questions

Unsupervised Learning of Morphological Forests


Feb 22, 2017
Jiaming Luo, Karthik Narasimhan, Regina Barzilay

* 12 pages, 5 figures, accepted by TACL 2017 

  Access Paper or Ask Questions

Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning


Sep 27, 2016
Karthik Narasimhan, Adam Yala, Regina Barzilay

* Appearing in EMNLP 2016 (12 pages incl. supplementary material) 

  Access Paper or Ask Questions

Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge


Aug 09, 2016
Nicholas Locascio, Karthik Narasimhan, Eduardo DeLeon, Nate Kushman, Regina Barzilay

* to be published in EMNLP 2016 

  Access Paper or Ask Questions

sk_p: a neural program corrector for MOOCs


Jul 11, 2016
Yewen Pu, Karthik Narasimhan, Armando Solar-Lezama, Regina Barzilay


  Access Paper or Ask Questions

Nonparametric Spherical Topic Modeling with Word Embeddings


Apr 01, 2016
Kayhan Batmanghelich, Ardavan Saeedi, Karthik Narasimhan, Sam Gershman


  Access Paper or Ask Questions

Language Understanding for Text-based Games Using Deep Reinforcement Learning


Sep 11, 2015
Karthik Narasimhan, Tejas Kulkarni, Regina Barzilay

* 11 pages, Appearing at EMNLP, 2015 

  Access Paper or Ask Questions

JUMP-Means: Small-Variance Asymptotics for Markov Jump Processes


Jun 05, 2015
Jonathan H. Huggins, Karthik Narasimhan, Ardavan Saeedi, Vikash K. Mansinghka

* JMLR: W&CP Volume 37, 2015 pp. 693-701 
* In Proceedings of the 32nd International Conference on Machine Learning (ICML 2015) 

  Access Paper or Ask Questions

An Unsupervised Method for Uncovering Morphological Chains


Mar 08, 2015
Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

* 11 pages, Appearing in the Transactions of the Association for Computational Linguistics (TACL), 2015 

  Access Paper or Ask Questions