We view large language models (LLMs) as stochastic language layers in
a ...
In this work we examine the ability of language models to generate expli...
Humans learn to master open-ended repertoires of skills by imagining and...
Building open-ended agents that can autonomously discover a diversity of...
Human intelligence can remarkably adapt quickly to new tasks and
environ...
The adoption of pre-trained language models to generate action plans for...
In this work, we explore techniques for augmenting interactive agents wi...
Text-based games offer a challenging test bed to evaluate virtual agents...
In this extended abstract we discuss the opportunities and challenges of...
We present the IGLU Gridworld: a reinforcement learning environment for
...
Human intelligence has the remarkable ability to adapt to new tasks and
...
To solve difficult tasks, humans ask questions to acquire knowledge from...
This paper presents a new benchmark, ScienceWorld, to test agents' scien...
Humans have the capability, aided by the expressive compositionality of ...
Given a simple request (e.g., Put a washed apple in the kitchen fridge),...
Graph neural networks (GNNs) have been attracting increasing popularity ...
Playing text-based games requires skill in processing natural language a...
We are interested in learning how to update Knowledge Graphs (KG) from t...
A hallmark of human intelligence is the ability to understand and commun...
Humans observe and interact with the world to acquire knowledge. However...
Existing machine reading comprehension (MRC) models do not scale effecti...
State representation learning, or the ability to capture latent generati...
To solve a text-based game, an agent needs to formulate valid text comma...
Recent work has shown how to learn better visual-semantic embeddings by
...
Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art...
We introduce TextWorld, a sandbox learning environment for the training ...
We propose a recurrent RL agent with an episodic exploration mechanism t...
Many efforts have been devoted to training generative latent variable mo...
Theano is a Python library that allows to define, optimize, and evaluate...
We present Neural Autoregressive Distribution Estimation (NADE) models, ...
We present a mathematical construction for the restricted Boltzmann mach...