
-
Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents
Text-based games simulate worlds and interact with players using natural...
read it
-
Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning
In this paper, we consider the problem of leveraging textual description...
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 ...
read it
-
Generating Strategic Dialogue for Negotiation with Theory of Mind
We propose a framework to integrate the concept of Theory of Mind (ToM) ...
read it
-
Safe Reinforcement Learning with Natural Language Constraints
In this paper, we tackle the problem of learning control policies for ta...
read it
-
Projection-Based Constrained Policy Optimization
We consider the problem of learning control policies that optimize a rew...
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...
read it
-
Guiding Attention for Self-Supervised Learning with Transformers
In this paper, we propose a simple and effective technique to allow for ...
read it
-
Learning Rewards from Linguistic Feedback
We explore unconstrained natural language feedback as a learning signal ...
read it
-
Towards Unique and Informative Captioning of Images
Despite considerable progress, state of the art image captioning models ...
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...
read it
-
Accelerating Safe Reinforcement Learning with Constraint-mismatched Policies
We consider the problem of reinforcement learning when provided with a b...
read it
-
Universal Adversarial Attacks with Natural Triggers for Text Classification
Recent work has demonstrated the vulnerability of modern text classifier...
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...
read it
-
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
We introduce a new algorithm for multi-objective reinforcement learning ...
read it
-
Calibration, Entropy Rates, and Memory in Language Models
Building accurate language models that capture meaningful long-term depe...
read it
-
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning
While model-based deep reinforcement learning (RL) holds great promise f...
read it
-
Deep Transfer in Reinforcement Learning by Language Grounding
In this paper, we explore the utilization of natural language to drive t...
read it
-
Representation Learning for Grounded Spatial Reasoning
The interpretation of spatial references is highly contextual, requiring...
read it
-
Unsupervised Learning of Morphological Forests
This paper focuses on unsupervised modeling of morphological families, c...
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...
read it
-
sk_p: a neural program corrector for MOOCs
We present a novel technique for automatic program correction in MOOCs, ...
read it
-
Nonparametric Spherical Topic Modeling with Word Embeddings
Traditional topic models do not account for semantic regularities in lan...
read it
-
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
Most successful information extraction systems operate with access to a ...
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...
read it
-
An Unsupervised Method for Uncovering Morphological Chains
Most state-of-the-art systems today produce morphological analysis based...
read it
-
JUMP-Means: Small-Variance Asymptotics for Markov Jump Processes
Markov jump processes (MJPs) are used to model a wide range of phenomena...
read it