Hierarchical reinforcement learning has been a compelling approach for
a...
Shannon, in his seminal paper introducing information theory, divided th...
What can be learned about causality and experimentation from passive dat...
Meta-learning is a framework for learning learning algorithms through
re...
Reasoning in a complex and ambiguous environment is a key goal for
Reinf...
Instruction-following agents must ground language into their observation...
A fundamental ability of an intelligent web-based agent is seeking out a...
Transformer models can use two fundamentally different kinds of informat...
Abstract reasoning is a key ability for an intelligent system. Large lan...
Strong inductive biases are a key component of human intelligence, allow...
Large language models can perform new tasks by adapting to a few in-cont...
The ability to acquire abstract knowledge is a hallmark of human intelli...
Weather sensing and forecasting has become increasingly accurate in the ...
Explanations play a considerable role in human learning, especially in a...
Despite the increasing scale of datasets in machine learning, generaliza...
Developments in machine learning interpretability techniques over the pa...
Modern machine learning models for computer vision exceed humans in accu...
Modern machine learning systems struggle with sample efficiency and are
...
As modern deep networks become more complex, and get closer to human-lik...
Discovering and exploiting the causal structure in the environment is a
...
An important frontier in the quest for human-like AI is compositional
se...