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

Autor:	Qiao, Ting, Williams, Henry, Valencia, David, MacDonald, Bruce
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Electrical Engineering and Systems Science - Systems and Control
Zdroj:	ISBN: 978-0-6455655-2-2 ISSN: 1448-2053
Druh dokumentu:	Working Paper
Popis:	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 out of 8 experiments. Bounded exploration presents an alternative method to introduce intrinsic motivations to exploration when the original reward function has strict meanings. Comment: 8 pages, 7 figures. Accepted as a poster presentation in the Australian Robotics and Automation Association (2023)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.06139 Zobrazit plný text záznamu View this record from Arxiv