Timezone: »

Unifying Count-Based Exploration and Intrinsic Motivation
Marc Bellemare · Sriram Srinivasan · Georg Ostrovski · Tom Schaul · David Saxton · Remi Munos

Wed Dec 07 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #71

We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across states. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncertainty, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. This technique enables us to generalize count-based exploration algorithms to the non-tabular case. We apply our ideas to Atari 2600 games, providing sensible pseudo-counts from raw pixels. We transform these pseudo-counts into exploration bonuses and obtain significantly improved exploration in a number of hard games, including the infamously difficult Montezuma's Revenge.

Author Information

Marc Bellemare (Google DeepMind)
Sriram Srinivasan (Google)
Georg Ostrovski (Google DeepMind)
Tom Schaul (DeepMind)
David Saxton (Google DeepMind)
Remi Munos (Google DeepMind)

More from the Same Authors