Unifying Count-Based Exploration and Intrinsic Motivation

TL;DR

This paper introduces a method that combines count-based exploration with intrinsic motivation using density models to improve exploration in non-tabular reinforcement learning, demonstrated on Atari games including Montezuma's Revenge.

Contribution

It presents a novel algorithm to derive pseudo-counts from arbitrary density models, enabling effective exploration in high-dimensional environments.

Findings

Significantly improved exploration in Atari games.

Effective pseudo-counts derived from raw pixel observations.

Enhanced performance in challenging exploration scenarios like Montezuma's Revenge.

Abstract

We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations. 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 intrinsic rewards and obtain significantly improved exploration in a number of hard games, including the infamously difficult Montezuma's Revenge.