- How can machines learn to represent the world, learn to predict, and learn to act largely by observation?
- Interactions in the real world are expensive and dangerous, intelligent agents should learn as much as they can about the world without interaction (by observation) so as to minimize the number of expensive and dangerous trials necessary to learn a particular task.
- How can machine reason and plan in ways that are compatible with gradient-based learning?
- Our best approaches to learning rely on estimating and using the gradient of a loss, which can only be performed with differentiable architectures and is difficult to rec- oncile with logic-based symbolic reasoning.
- How can machines learn to represent percepts and action plans in a hierarchical manner, at multiple levels of abstraction, and multiple time scales?
- Humans and many animals are able to conceive multilevel abstractions with which long-term predictions and long-term planning can be performed by decomposing com- plex actions into sequences of lower-level ones.