Deep reinforcement learning (RL) has emerged as a promising approach for autonomously
acquiring complex behaviors from low-level sensor observations. Although a large portion of …

Traditionally, cognitive and computer scientists have viewed intelligence solipsistically, as a
property of unitary agents devoid of social context. Given the success of contemporary …

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more
quickly, by leveraging prior experience to learn how to learn. However, much of the current …

While deep learning and deep reinforcement learning (RL) systems have demonstrated
impressive results in domains such as image classification, game playing, and robotic …

General-purpose robotic systems must master a large repertoire of diverse skills to be useful
in a range of daily tasks. While reinforcement learning provides a powerful framework for …

Model-based reinforcement learning (MBRL) is widely seen as having the potential to be
significantly more sample efficient than model-free RL. However, research in model-based …

In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for
several tasks. Joint training reduces computation costs and improves data efficiency; …

Autonomous agents must often deal with conflicting requirements, such as completing tasks
using the least amount of time/energy, learning multiple tasks, or dealing with multiple …

Abstract Continual learning (CL)---the ability to continuously learn, building on previously
acquired knowledge---is a natural requirement for long-lived autonomous reinforcement …

Offline reinforcement learning (RL) algorithms have shown promising results in domains
where abundant pre-collected data is available. However, prior methods focus on solving …