An important goal in artificial intelligence is to create agents that ca...
Creating agents that can interact naturally with humans is a common goal...
A common vision from science fiction is that robots will one day inhabit...
Imitation learning enables agents to reuse and adapt the hard-won expert...
Since the earliest days of reinforcement learning, the workhorse method ...
A common vision from science fiction is that robots will one day inhabit...
We propose the Gaussian Gated Linear Network (G-GLN), an extension to th...
An ideal cognitively-inspired memory system would compress and organize
...
We consider the problem of efficient credit assignment in reinforcement
...
Both in simulation settings and robotics, there is an ambition to produc...
The measurement of time is central to intelligent behavior. We know that...
As reinforcement learning agents are tasked with solving more challengin...
The field of reinforcement learning (RL) is facing increasingly challeng...
We focus on the problem of learning a single motor module that can flexi...
Continual learning is the problem of learning new tasks or knowledge whi...
We aim to build complex humanoid agents that integrate perception, motor...
A central challenge faced by memory systems is the robust retrieval of a...
Humans spend a remarkable fraction of waking life engaged in acts of "me...
We present an end-to-end trained memory system that quickly adapts to ne...
In order to build agents with a rich understanding of their environment,...
Animals execute goal-directed behaviours despite the limited range and s...
The reinforcement learning paradigm allows, in principle, for complex
be...
We consider the general problem of modeling temporal data with long-rang...
Neural networks augmented with external memory have the ability to learn...
We study a novel architecture and training procedure for locomotion task...
We investigate a new method to augment recurrent neural networks with ex...
We present a unified framework for learning continuous control policies ...
We extend the capabilities of neural networks by coupling them to extern...