文章基本信息

标题：Smart Start and HER for a Directed and Persistent Reinforcement Learning Exploration in Discrete Environment
其他标题：Smart Start and HER for a Directed and Persistent Reinforcement Learning Exploration in Discrete Environment
本地全文：下载
作者：Heba Alrakh ; Muhammad Fahmi Miskon ; Rozilawati Mohd Nor 等
期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2020
卷号：11
期号：11
DOI：10.14569/IJACSA.2020.0111117
出版社：Science and Information Society (SAI)
摘要：Reinforcement learning (RL) solves sequential decision making problems through trial and error, through experiences can be amassed to achieve goals and increase the accumulative rewards. Exploration-exploitation dilemma is a critical challenge in reinforcement learning, particularly environments with misleading or sparse rewards which have shown difficulties to construct a suitable exploration strategy. In this paper a framework for Smart Start (SS) and Hindsight experience replay (HER) is developed to improve the performance of SS and make the exploration more directed especially in the early episodes. The framework Smart Start and Hindsight experience replay (SS HER) was studied in discrete maze environment with sparse rewards. The results reveal that the framework doubles the rewards at the early episodes and decreases the time of the agent to reach the goal.
关键词：Reinforcement learning; hindsight experience replay; smart start; limit search space; exploration-exploitation trade off