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

[1] Policy Reuse in Reinforcement Learning for Modular Agents
Raza, Sayyed Jaffar Ali
Lin, Mingjie
2019 IEEE 2ND INTERNATIONAL CONFERENCE ON INFORMATION AND COMPUTER TECHNOLOGIES (ICICT), 2019, : 165 - 169
[2] Modular Multitask Reinforcement Learning with Policy Sketches
Andreas, Jacob
Klein, Dan
Levine, Sergey
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
[3] Adaptable automation with modular deep reinforcement learning and policy transfer
Raziei, Zohreh
Moghaddam, Mohsen
Engineering Applications of Artificial Intelligence, 2021, 103
[4] Adaptable automation with modular deep reinforcement learning and policy transfer
Raziei, Zohreh
Moghaddam, Mohsen
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2021, 103
[5] Global structure of policy search spaces for reinforcement learning
Stapelberg, B.
Malan, K. M.
PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION (GECCCO'19 COMPANION), 2019, : 1773 - 1781
[6] Composable Modular Reinforcement Learning
Simpkins, Christopher
Isbell, Charles
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 4975 - 4982
[7] Modular production control using deep reinforcement learning: proximal policy optimization
Sebastian Mayer
Tobias Classen
Christian Endisch
Journal of Intelligent Manufacturing, 2021, 32 : 2335 - 2351
[8] MER: Modular Element Randomization for robust generalizable policy in deep reinforcement learning
Li, Yihan
Ren, Jinsheng
Zhang, Tianren
Fang, Ying
Chen, Feng
KNOWLEDGE-BASED SYSTEMS, 2023, 273
[9] Modular production control using deep reinforcement learning: proximal policy optimization
Mayer, Sebastian
Classen, Tobias
Endisch, Christian
JOURNAL OF INTELLIGENT MANUFACTURING, 2021, 32 (08) : 2335 - 2351
[10] Assessing Policy, Loss and Planning Combinations in Reinforcement Learning Using a New Modular Architecture
Oliveira, Tiago Gaspar
Oliveira, Arlindo L.
PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2022, 2022, 13566 : 427 - 439

← 1 2 3 4 5 →