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

[31] Construction of Polar Codes With Reinforcement Learning
Liao, Yun
Hashemi, Seyyed Ali
Cioffi, John M.
Goldsmith, Andrea
IEEE TRANSACTIONS ON COMMUNICATIONS, 2022, 70 (01) : 185 - 198
[32] Feature construction for reinforcement learning in hearts
Sturtevant, Nathan R.
White, Adam M.
COMPUTERS AND GAMES, 2007, 4630 : 122 - +
[33] Construction of Approximation Spaces for Reinforcement Learning
Boehmer, Wendelin
Gruenewaelder, Steffen
Shen, Yun
Musial, Marek
Obermayer, Klaus
JOURNAL OF MACHINE LEARNING RESEARCH, 2013, 14 : 2067 - 2118
[34] Construction of approximation spaces for reinforcement learning
Neural Information Processing Group, Technische Universität Berlin, Marchstrasse 23, Berlin 10587, Germany
不详
不详
J. Mach. Learn. Res., 2013, (2067-2118):
[35] Construction of Polar Codes with Reinforcement Learning
Liao, Yun
Hashemi, Seyyed Ali
Cioffi, John
Goldsmith, Andrea
2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2020,
[36] Survey on policy reuse in reinforcement learning
He L.
Shen L.
Li H.
Wang Z.
Tang W.
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2022, 44 (03): : 884 - 899
[37] Expected Policy Gradients for Reinforcement Learning
Ciosek, Kamil
Whiteson, Shimon
JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
[38] Policy Optimization for Continuous Reinforcement Learning
Zhao, Hanyang
Tang, Wenpin
Yao, David D.
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[39] Policy Consolidation for Continual Reinforcement Learning
Kaplanis, Christos
Shanahan, Murray
Clopath, Claudia
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
[40] Policy Reuse in Deep Reinforcement Learning
Glatt, Ruben
Helena, Anna
Costa, Reali
THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 4929 - 4930

← 1 2 3 4 5 →