Unifying Count-Based Exploration and Intrinsic Motivation
This addresses the challenge of efficient exploration in complex environments for reinforcement learning agents, representing a novel method rather than an incremental improvement.
The paper tackled the problem of exploration in non-tabular reinforcement learning by proposing a method to derive pseudo-counts from density models, enabling generalization of count-based exploration. The result was significantly improved exploration in Atari 2600 games, including Montezuma's Revenge, with concrete performance gains.
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.