Hierarchical Reinforcement Learning: A Survey and Open Research Challenges

Hutsebaut-Buysse Matthias; Mets Kevin; Latre Steven

首页> 外文期刊>Machine Learning and Knowledge Extraction >Hierarchical Reinforcement Learning: A Survey and Open Research Challenges

【24h】

Hierarchical Reinforcement Learning: A Survey and Open Research Challenges

机译：

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutions often fails, or is very sample inefficient, requiring an unreasonable amount of interaction with the environment. Hierarchical reinforcement learning (HRL) utilizes forms of temporal- and state-abstractions in order to tackle these challenges, while simultaneously paving the road for behavior reuse and increased interpretability of RL systems. In this survey paper we first introduce a selection of problem-specific approaches, which provided insight in how to utilize often handcrafted abstractions in specific task settings. We then introduce the Options framework, which provides a more generic approach, allowing abstractions to be discovered and learned semi-automatically. Afterwards we introduce the goal-conditional approach, which allows sub-behaviors to be embedded in a continuous space. In order to further advance the development of HRL agents, capable of simultaneously learning abstractions and how to use them, solely from interaction with complex high dimensional environments, we also identify a set of promising research directions.

著录项

来源
《Machine Learning and Knowledge Extraction》 |2022年第1期|172-221|共50页
作者
Hutsebaut-Buysse Matthias; Mets Kevin; Latre Steven;
展开▼
作者单位

Univ Antwerp imec;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词
hierarchical reinforcement learning; deep reinforcement learning; reinforcement learning; DEEP NEURAL-NETWORKS; LEVEL; ABSTRACTION; FRAMEWORK; OPTIONS;

相似文献

外文文献
中文文献
专利

1. Hierarchical Reinforcement Learning: A Comprehensive Survey [J] . SHUBHAM PATERIA, BUDHITAMA SUBAGDJA, AH-HWEE TANCHAI QUEK ACM computing surveys . 2022,第5期

机译：Hierarchical Reinforcement Learning: A Comprehensive Survey
2. New challenges in reinforcement learning: a survey of security and privacy [J] . Lei Yunjiao, Ye Dayong, Shen ShengSui YuleiZhu TianqingZhou Wanlei Artificial Intelligence Review: An International Science and Engineering Journal . 2023,第7期

机译：New challenges in reinforcement learning: a survey of security and privacy
3. Hierarchical reinforcement learning for motion learning: learning 'stand-up' trajectories [J] . Jun Morimoto, Kenji Doya advanced robotics . 1998,第3期

机译：Hierarchical reinforcement learning for motion learning: learning 'stand-up' trajectories
4. 探测机器人路径规划的基于案例的强化学习算法A Case-Based Reinforcement Learning for Probe Robot Path Planning [C] . . 2002

机译：探测机器人路径规划的基于案例的强化学习算法A Case-Based Reinforcement Learning for Probe Robot Path Planning
5. Genetic Basis of Disease Resilience in Wean-To-Finish Pigs Under a Natural Disease Challenge Model =自然攻毒下断奶育肥猪的抗病遗传基础 [D] . Cheng, Jian. 2021

机译：Genetic Basis of Disease Resilience in Wean-To-Finish Pigs Under a Natural Disease Challenge Model =自然攻毒下断奶育肥猪的抗病遗传基础
6. Deep Q-Learning for Two-Hop Communications of Drone Base Stations [O] . Azade Fotouhi, Ming Ding, Mahbub Hassan 2021

机译：深度Q-Learning为无人机基站的两跳通信
7. 学习者自主性层级阐释与多维发展的研究Hierarchy Analysis and Multidimensional Development of Autonomy in Learning [O] . 申宝国 2013

机译：学习者自主性层级阐释与多维发展的研究Hierarchy Analysis and Multidimensional Development of Autonomy in Learning
8. Osse Sky Survey Observations for Cycles Three Extreme Red Egret Blazars [R] . Schachter, J. F. 1998

机译：Osse sky survey survey for Cycles Three Extreme Redret Blazars

Hierarchical Reinforcement Learning: A Survey and Open Research Challenges

摘要

著录项

相似文献

相关主题

期刊订阅