It has long been established that predictive models can be transformed i...
Transformers have impressive generalization capabilities on tasks with a...
Memory-based meta-learning is a technique for approximating Bayes-optima...
Meta-training agents with memory has been shown to culminate in Bayes-op...
The recent phenomenal success of language models has reinvigorated machi...
Reinforcement Learning formalises an embodied agent's interaction with t...
Human intelligence is characterized not only by the capacity to learn co...
We propose the Gaussian Gated Linear Network (G-GLN), an extension to th...
We introduce a new and completely online contextual bandit algorithm cal...
This paper presents a family of backpropagation-free neural architecture...
In this report we review memory-based meta-learning as a tool for buildi...
This paper describes a family of probabilistic architectures designed fo...
The ability to learn tasks in a sequential fashion is crucial to the
dev...
This paper describes a new information-theoretic policy evaluation techn...
This paper introduces the Partition Tree Weighting technique, an efficie...
In this article we introduce the Arcade Learning Environment (ALE): both...
The Universal Intelligence Measure is a recently proposed formal definit...
This paper introduces a principled approach for the design of a scalable...