Global Policy Construction in Modular Reinforcement Learning

被引：0

作者：

Zhang, Ruohan ^{[1
]}

Song, Zhao ^{[1
]}

Ballard, Dana H. ^{[1
]}

机构：

[1] Univ Texas Austin, Dept Comp Sci, 2317 Speedway,Stop D9500, Austin, TX 78712 USA

来源：

PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | 2015年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose a modular reinforcement learning algorithm which decomposes a Markov decision process into independent modules. Each module is trained using Sarsa(lambda). We introduce three algorithms for forming global policy from modules policies, and demonstrate our results using a 2D grid world.

引用

页码：4226 / 4227

页数：2

共 50 条

[41] Evolving Constrained Reinforcement Learning Policy
Hu, Chengpeng
Pei, Jiyuan
Liu, Jialin
Yao, Xin
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
[42] Expected policy gradients for reinforcement learning
Ciosek, Kamil
Whiteson, Shimon
Journal of Machine Learning Research, 2020, 21
[43] On-policy concurrent reinforcement learning
Banerjee, B
Sen, S
Peng, J
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2004, 16 (04) : 245 - 260
[44] Policy gradient fuzzy reinforcement learning
Wang, XN
Xu, X
He, HG
PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, : 992 - 995
[45] Modular Reinforcement Learning for Autonomous UAV Flight Control
Choi, Jongkwan
Kim, Hyeon Min
Hwang, Ha Jun
Kim, Yong-Duk
Kim, Chang Ouk
DRONES, 2023, 7 (07)
[46] A modular approach to multi-agent reinforcement learning
Ono, N
Fukumoto, K
DISTRIBUTED ARTIFICIAL INTELLIGENCE MEETS MACHINE LEARNING: LEARNING IN MULTI-AGENT ENVIRONMENTS, 1997, 1221 : 25 - 39
[47] Modular reinforcement learning:: An application to a real robot task
Kalmár, Z
Szepesvári, C
Lörincz, A
LEARNING ROBOTS, PROCEEDINGS, 1998, 1545 : 29 - 45
[48] Modular Robot Design Synthesis with Deep Reinforcement Learning
Whitman, Julian
Bhirangi, Raunaq
Travers, Matthew
Choset, Howie
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 10418 - 10425
[49] A modular framework for stabilizing deep reinforcement learning control
Lawrence, Nathan P.
Loewen, Philip D.
Wang, Shuyuan
Forbes, Michael G.
Gopaluni, R. Bhushan
IFAC PAPERSONLINE, 2023, 56 (02): : 8006 - 8011
[50] MANDREL: Modular Reinforcement Learning Pipelines for Material Discovery
Fare, Clyde
Holt, George K.
Chiazor, Lamogha
Smyrnakis, Michalis
Tracey, Robert
Hoang, Lan
THIRTY-EIGTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 21, 2024, : 23787 - 23789

← 1 2 3 4 5 →