Reinforcement learning is bedeviled by the curse of dimensionality: the number of
parameters to be learned grows exponentially with the size of any compact encoding of a …

Research on human and animal behavior has long emphasized its hierarchical structure—
the divisibility of ongoing behavior into discrete tasks, which are comprised of subtask …

As a step towards developing zero-shot task generalization capabilities in reinforcement
learning (RL), we introduce a new RL problem where the agent should learn to execute …

Psychologists call behavior intrinsically motivated when it is engaged in for its own sake
rather than as a step toward solving a specific problem of clear practical value. But what we …

It is now widely accepted that instrumental actions can be either goal‐directed or habitual;
whereas the former are rapidly acquired and regulated by their outcome, the latter are …

Humans and other animals often engage in activities for their own sakes rather than as steps
toward solving practical problems. Psychologists call these intrinsically motivated behaviors …

This paper introduces a novel spectral framework for solving Markov decision processes
(MDPs) by jointly learning representations and optimal policies. The major components of …

We present a new method for automatically creating useful temporal abstractions in
reinforcement learning. We argue that states that allow the agent to transition to a different …

We introduce a new skill-discovery algorithm that builds a discrete graph representation of
large continuous MDPs, where nodes correspond to skill subgoals and the edges to skill …

Contingency awareness is the recognition that some aspects of a future observation are
under an agent's control while others are solely determined by the environment. This paper …