Deep reinforcement learning is the combination of reinforcement learning (RL) and deep
learning. This field of research has been able to solve a wide range of complex …

Value-function approximation methods that operate in batch mode have foundational
importance to reinforcement learning (RL). Finite sample guarantees for these methods …

We present an algorithm, HOMER, for exploration and reinforcement learning in rich
observation environments that are summarizable by an unknown latent state space. The …

In reinforcement learning (RL), representation learning is a proven tool for complex image-
based tasks, but is often overlooked for environments with low-level states, such as physical …

The reinforcement learning paradigm is a popular way to address problems that have only
limited environmental feedback, rather than correctly labeled examples, as is common in …

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant
information from complex observations, balancing between robustness to distraction and …

Incorporating symmetries can lead to highly data-efficient and generalizable models by
defining equivalence classes of data samples related by transformations. However …

We propose a simple, practical, and intuitive approach for domain adaptation in
reinforcement learning. Our approach stems from the idea that the agent's experience in the …

Learning dynamics models accurately is an important goal for Model-Based Reinforcement
Learning (MBRL), but most MBRL methods learn a dense dynamics model which is …

Abstraction has been widely studied as a way to improve the efficiency and generalization of
reinforcement learning algorithms. In this paper, we study abstraction in the continuous …