Exploration in Deep Reinforcement Learning: A Survey

TL;DR

This survey comprehensively reviews exploration techniques in deep reinforcement learning, emphasizing methods for sparse reward problems and discussing future research directions and performance comparisons.

Contribution

It categorizes existing exploration methods in deep reinforcement learning and analyzes their complexity, effectiveness, and challenges, providing a valuable overview for future research.

Findings

Different exploration approaches are categorized and compared.

Sparse reward problems require sophisticated exploration strategies.

Future research directions are identified and discussed.

Abstract

This paper reviews exploration techniques in deep reinforcement learning. Exploration techniques are of primary importance when solving sparse reward problems. In sparse reward problems, the reward is rare, which means that the agent will not find the reward often by acting randomly. In such a scenario, it is challenging for reinforcement learning to learn rewards and actions association. Thus more sophisticated exploration methods need to be devised. This review provides a comprehensive overview of existing exploration approaches, which are categorized based on the key contributions as follows reward novel states, reward diverse behaviours, goal-based methods, probabilistic methods, imitation-based methods, safe exploration and random-based methods. Then, the unsolved challenges are discussed to provide valuable future research directions. Finally, the approaches of different categories are compared in terms of complexity, computational effort and overall performance.