Dropped into an unknown environment, what should an agent do to quickly ...
Building generally capable agents is a grand challenge for deep reinforc...
How can artificial agents learn to solve many diverse tasks in complex v...
Training visuomotor robot controllers from scratch on a new robot typica...
The ability to plan into the future while utilizing only raw high-dimens...
Reinforcement learning is a powerful framework for robots to acquire ski...
The ability to predict and plan into the future is fundamental for agent...
Variational autoencoders (VAEs) provide an effective and simple method f...
Reinforcement learning allows solving complex tasks, however, the learni...
Learning predictive models from interaction with the world allows an age...
Real-world image sequences can often be naturally decomposed into a smal...
Recently, much progress has been made building systems that can capture
...
An intelligent observer looks at the world and sees not only what is, bu...