Karthik Narasimhan

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

Text-based games simulate worlds and interact with players using natural...
03/25/2021 ∙ by Shunyu Yao, et al. ∙ 0 ∙ share

read it
Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning

In this paper, we consider the problem of leveraging textual description...
01/19/2021 ∙ by H. J. Austin Wang, et al. ∙ 0 ∙ share

read it
Connecting Context-specific Adaptation in Humans to Meta-learning

Cognitive control, the ability of a system to adapt to the demands of a ...
11/27/2020 ∙ by Rachit Dubey, et al. ∙ 0 ∙ share

read it
Generating Strategic Dialogue for Negotiation with Theory of Mind

We propose a framework to integrate the concept of Theory of Mind (ToM) ...
10/20/2020 ∙ by Runzhe Yang, et al. ∙ 0 ∙ share

read it
Safe Reinforcement Learning with Natural Language Constraints

In this paper, we tackle the problem of learning control policies for ta...
10/11/2020 ∙ by Tsung-Yen Yang, et al. ∙ 27 ∙ share

read it
Projection-Based Constrained Policy Optimization

We consider the problem of learning control policies that optimize a rew...
10/07/2020 ∙ by Tsung-Yen Yang, et al. ∙ 0 ∙ share

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

Text-based games present a unique challenge for autonomous agents to ope...
10/06/2020 ∙ by Shunyu Yao, et al. ∙ 0 ∙ share

read it
Guiding Attention for Self-Supervised Learning with Transformers

In this paper, we propose a simple and effective technique to allow for ...
10/06/2020 ∙ by Ameet Deshpande, et al. ∙ 0 ∙ share

read it
Learning Rewards from Linguistic Feedback

We explore unconstrained natural language feedback as a learning signal ...
09/30/2020 ∙ by Theodore R. Sumers, et al. ∙ 0 ∙ share

read it
Towards Unique and Informative Captioning of Images

Despite considerable progress, state of the art image captioning models ...
09/08/2020 ∙ by Zeyu Wang, et al. ∙ 7 ∙ share

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

The ability to perform effective planning is crucial for building an ins...
07/11/2020 ∙ by Zhiwei Deng, et al. ∙ 11 ∙ share

read it
Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies

We consider the problem of reinforcement learning when provided with a b...
06/20/2020 ∙ by Tsung-Yen Yang, et al. ∙ 0 ∙ share

read it
Universal Adversarial Attacks with Natural Triggers for Text Classification

Recent work has demonstrated the vulnerability of modern text classifier...
05/01/2020 ∙ by Liwei Song, et al. ∙ 0 ∙ share

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

In the Vision-and-Language Navigation (VLN) task, an agent with egocentr...
03/31/2020 ∙ by Felix Yu, et al. ∙ 0 ∙ share

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

We introduce a new algorithm for multi-objective reinforcement learning ...
08/21/2019 ∙ by Runzhe Yang, et al. ∙ 0 ∙ share

read it
Calibration, Entropy Rates, and Memory in Language Models

Building accurate language models that capture meaningful long-term depe...
06/11/2019 ∙ by Mark Braverman, et al. ∙ 1 ∙ share

read it
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning

While model-based deep reinforcement learning (RL) holds great promise f...
05/13/2019 ∙ by Yilun Du, et al. ∙ 0 ∙ share

read it
Deep Transfer in Reinforcement Learning by Language Grounding

In this paper, we explore the utilization of natural language to drive t...
08/01/2017 ∙ by Karthik Narasimhan, et al. ∙ 0 ∙ share

read it
Representation Learning for Grounded Spatial Reasoning

The interpretation of spatial references is highly contextual, requiring...
07/13/2017 ∙ by Michael Janner, et al. ∙ 0 ∙ share

read it
Unsupervised Learning of Morphological Forests

This paper focuses on unsupervised modeling of morphological families, c...
02/22/2017 ∙ by Jiaming Luo, et al. ∙ 0 ∙ share

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

This paper explores the task of translating natural language queries int...
08/09/2016 ∙ by Nicholas Locascio, et al. ∙ 0 ∙ share

read it
sk_p: a neural program corrector for MOOCs

We present a novel technique for automatic program correction in MOOCs, ...
07/11/2016 ∙ by Yewen Pu, et al. ∙ 0 ∙ share

read it
Nonparametric Spherical Topic Modeling with Word Embeddings

Traditional topic models do not account for semantic regularities in lan...
04/01/2016 ∙ by Kayhan Batmanghelich, et al. ∙ 0 ∙ share

read it
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning

Most successful information extraction systems operate with access to a ...
03/25/2016 ∙ by Karthik Narasimhan, et al. ∙ 0 ∙ share

read it
Language Understanding for Text-based Games Using Deep Reinforcement Learning

In this paper, we consider the task of learning control policies for tex...
06/30/2015 ∙ by Karthik Narasimhan, et al. ∙ 0 ∙ share

read it
An Unsupervised Method for Uncovering Morphological Chains

Most state-of-the-art systems today produce morphological analysis based...
03/08/2015 ∙ by Karthik Narasimhan, et al. ∙ 0 ∙ share

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

Markov jump processes (MJPs) are used to model a wide range of phenomena...
03/01/2015 ∙ by Jonathan H. Huggins, et al. ∙ 0 ∙ share

read it

Karthik Narasimhan

Featured Co-authors

Yi Zhang

Regina Barzilay

Sham M. Kakade

Thomas L. Griffiths

Tommi Jaakkola

Armando Solar-Lezama

Yinlam Chow

Olga Russakovsky

Vikash K. Mansinghka

Matthew Hausknecht

Jonathan H. Huggins

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

Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning

Connecting Context-specific Adaptation in Humans to Meta-learning

Generating Strategic Dialogue for Negotiation with Theory of Mind

Safe Reinforcement Learning with Natural Language Constraints

Projection-Based Constrained Policy Optimization

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

Guiding Attention for Self-Supervised Learning with Transformers

Learning Rewards from Linguistic Feedback

Towards Unique and Informative Captioning of Images

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

Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies

Universal Adversarial Attacks with Natural Triggers for Text Classification

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

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

Calibration, Entropy Rates, and Memory in Language Models

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning

Deep Transfer in Reinforcement Learning by Language Grounding

Representation Learning for Grounded Spatial Reasoning

Unsupervised Learning of Morphological Forests

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

sk_p: a neural program corrector for MOOCs

Nonparametric Spherical Topic Modeling with Word Embeddings

Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning

Language Understanding for Text-based Games Using Deep Reinforcement Learning

An Unsupervised Method for Uncovering Morphological Chains

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