A Core Task Abstraction Approach to Hierarchical Reinforcement Learning

被引：0
|
作者：
Li, Zhuoru [1 ]
Narayan, Akshay [1 ]
Leong, Tze-Yun [1 ,2 ]
机构：
[1] Natl Univ Singapore, Sch Comp, Singapore, Singapore
[2] Singapore Management Univ, Sch Informat Syst, Singapore, Singapore
来源：
AAMAS'16: PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS | 2016年
关键词：
hierarchical reinforcement learning; core task abstraction;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
We propose a new, core task abstraction (CTA) approach to learning the relevant transition functions in model-based hierarchical reinforcement learning. CTA exploits contextual independences of the state variables conditional on the taskspecific actions; its promising performance is demonstrated through a set of benchmark problems.
引用
收藏
页码：1411 / 1412
页数：2
相关论文
共 50 条
  • [1] State abstraction in MAXQ hierarchical reinforcement learning
    Dietterich, TG
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 12, 2000, 12 : 994 - 1000
  • [2] Language as an Abstraction for Hierarchical Deep Reinforcement Learning
    Jiang, Yiding
    Gu, Shixiang
    Murphy, Kevin
    Finn, Chelsea
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [3] Research on task decomposition and state abstraction in reinforcement learning
    Yu Lasheng
    Jiang Zhongbin
    Liu Kang
    [J]. Artificial Intelligence Review, 2012, 38 : 119 - 127
  • [4] Research on task decomposition and state abstraction in reinforcement learning
    Yu Lasheng
    Jiang Zhongbin
    Liu Kang
    [J]. ARTIFICIAL INTELLIGENCE REVIEW, 2012, 38 (02) : 119 - 127
  • [5] Hierarchical reinforcement learning for Metrical Task Systems
    de Lima, ML
    de Melo, JD
    Neto, ADD
    [J]. HIS 2005: 5TH INTERNATIONAL CONFERENCE ON HYBRID INTELLIGENT SYSTEMS, PROCEEDINGS, 2005, : 251 - 256
  • [6] Hierarchical Task Decomposition through Symbiosis in Reinforcement Learning
    Doucette, John A.
    Lichodzijewski, Peter
    Heywood, Malcolm I.
    [J]. PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL CONFERENCE ON GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2012, : 97 - 104
  • [7] Hierarchical Reinforcement Learning Explains Task Interleaving Behavior
    Gebhardt C.
    Oulasvirta A.
    Hilliges O.
    [J]. Computational Brain & Behavior, 2021, 4 (3) : 284 - 304
  • [8] Safe state abstraction and reusable continuing subtasks in hierarchical reinforcement learning
    Hengst, Bernhard
    [J]. AI 2007: ADVANCES IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2007, 4830 : 58 - 67
  • [9] A novel graphical approach to automatic abstraction in reinforcement learning
    Taghizadeh, Nasrin
    Beigy, Hamid
    [J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2013, 61 (08) : 821 - 835
  • [10] Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
    Kulkarni, Tejas D.
    Narasimhan, Karthik R.
    Saeedi, Ardavan
    Tenenbaum, Joshua B.
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29
12345