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 …
A Dezfouli, BW Balleine - European Journal of Neuroscience, 2012 - Wiley Online Library
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 …
Ö Şimşek, AG Barto - Proceedings of the twenty-first international …, 2004 - dl.acm.org
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 …
A Bagaria, JK Senthil… - … Conference on Machine …, 2021 - proceedings.mlr.press
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 …