Intelligent agents rely heavily on prior experience when learning a new task, yet most
modern reinforcement learning (RL) approaches learn every task from scratch. One …

Demonstration-guided reinforcement learning (RL) is a promising approach for learning
complex behaviors by leveraging both reward feedback and a set of target task …

We tackle real-world long-horizon robot manipulation tasks through skill discovery. We
present a bottom-up approach to learning a library of reusable skills from unsegmented …

The ability to predict and plan into the future is fundamental for agents acting in the world. To
reach a faraway goal, we predict trajectories at multiple timescales, first devising a coarse …

We introduce a variational approach to learning and inference of temporally hierarchical
structure and representation for sequential data. We propose the Variational Temporal …

When autonomous vehicles are deployed on public roads, they will encounter countless and
diverse driving situations. Many manually designed driving policies are difficult to scale to …

Efficient and effective exploration in continuous space is a central problem in applying
reinforcement learning (RL) to autonomous driving. Skills learned from expert …

To flexibly and efficiently reason about dynamics of temporal sequences, abstract
representations that compactly represent the important information in the sequence are …

In many real-world scenarios, an autonomous agent often encounters various tasks within a
single complex environment. We propose to build a graph abstraction over the environment …

This thesis, written for the qualification of Doctor of Philosophy in Computer Science, studies
the question of the individual importance of actions in sequential decision-making, through …