From Psychological Curiosity to Artificial Curiosity: Curiosity-Driven Learning in Artificial Intelligence Tasks
It addresses the problem of improving AI learning efficiency and generalization for researchers by bridging psychological principles with AI applications, but it is incremental as it primarily reviews and synthesizes existing work.
This paper reviews psychological curiosity and artificial curiosity-driven learning (CDL) in AI, summarizing a unified framework for quantifying curiosity and surveying CDL methods in Reinforcement Learning, Recommendation, and Classification to provide insights for future research.
Psychological curiosity plays a significant role in human intelligence to enhance learning through exploration and information acquisition. In the Artificial Intelligence (AI) community, artificial curiosity provides a natural intrinsic motivation for efficient learning as inspired by human cognitive development; meanwhile, it can bridge the existing gap between AI research and practical application scenarios, such as overfitting, poor generalization, limited training samples, high computational cost, etc. As a result, curiosity-driven learning (CDL) has become increasingly popular, where agents are self-motivated to learn novel knowledge. In this paper, we first present a comprehensive review on the psychological study of curiosity and summarize a unified framework for quantifying curiosity as well as its arousal mechanism. Based on the psychological principle, we further survey the literature of existing CDL methods in the fields of Reinforcement Learning, Recommendation, and Classification, where both advantages and disadvantages as well as future work are discussed. As a result, this work provides fruitful insights for future CDL research and yield possible directions for further improvement.