Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithm

作     者：Qiao, Ting Williams, Henry Valencia, David MacDonald, Bruce 

作者机构：Centre for Automation and Robotic Engineering Science The University of Auckland New Zealand 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Adversarial machine learning 

摘      要：One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration, a novel exploration method that integrates both soft and intrinsic motivation exploration. Bounded exploration notably improved the Soft Actor-Critic algorithm s performance and its model-based extension s converging speed. It achieved the highest score in 6/8 experiments. Bounded exploration presents an alternative method to introduce intrinsic motivations to exploration when the original reward function has strict meanings. © 2024, CC BY.