This open-source book represents our attempt to make deep learning approachable,
teaching readers the concepts, the context, and the code. The entire book is drafted in …

Highlights•Reinforcement learning (RL) provides a rich conceptual framework for
understanding human learning and decision making.•Most RL-inspired research in cognitive …

We study the problem of representation learning in goal-conditioned hierarchical
reinforcement learning. In such hierarchical structures, a higher-level controller solves tasks …

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 …

This review addresses the problem of learning abstract representations of the measurement
data in the context of Deep Reinforcement Learning (DRL). While the data are often …

The options framework provides a method for reinforcement learning agents to build new
high-level skills. However, since options are usually learned in the same state space as the …

One of the field in which models of abstraction have been proposed is Artificial Intelligence
(AI). This chapter has two parts: one presents an overview of the formal models, either …

We propose that humans spontaneously organize environments into clusters of states that
support hierarchical planning, enabling them to tackle challenging problems by breaking …

We study the question of how to imitate tasks across domains with discrepancies such as
embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned …

Abstraction can improve the sample efficiency of reinforcement learning. However, the
process of abstraction inherently discards information, potentially compromising an agent's …