"The Most Exacting Critic."

Exacting N = 4 Superconformal Symmetry

The Eigenoption-Critic Framework

Eigenoptions (EOs) have been recently introduced as a promising idea for generating a diverse set of options through the graph Laplacian, having been shown to allow efficient exploration Machado et al. [2017a]. Despite its first initial promising results, a couple of issues in current algorithms limit its application, namely: 1) EO methods require two separate steps (eigenoption discovery and r...

Empathy and the Critic

Ann Jurecic is assistant professor in the Department of English at Rutgers University, New Brunswick, where she teaches courses in writing as well as literature and medicine. Her book Illness as Narrative is forthcoming from University of Pittsburgh Press. Her work has appeared in the journals Literature and Medicine, Pedagogy, and Biography as well as in College English, and she serves as book...

The Well-Tempered Critic

The Option-Critic Architecture

Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We tackle this problem in the framework of options [Sutton, Precup & Singh, 1999; Precup, 2000]. We derive policy gradient theorems for options and propose a new ...