Argumentation accelerated reinforcement learning for cooperative multi-agent systems

Yang Gao; Francesca Toni

doi:10.3233/978-1-61499-419-0-333

Argumentation accelerated reinforcement learning for cooperative multi-agent systems

Yang Gao, Francesca Toni

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Multi-Agent Learning is a complex problem, especially in real-time systems. We address this problem by introducing Argumentation Accelerated Reinforcement Learning (AARL), which provides a methodology for defining heuristics, represented by arguments, and incorporates these heuristics into Reinforcement Learning (RL) by using reward shaping. We define AARL via argumentation and prove that it can coordinate independent cooperative agents that have a shared goal but need to perform different actions. We test AARL empirically in a popular RL testbed, RoboCup Takeaway, and show that it significantly improves upon standard RL.

Original language	English
Title of host publication	ECAI'14 Proceedings of the Twenty-first European Conference on Artificial Intelligence
Publisher	IOS Press
Pages	333-338
Number of pages	6
ISBN (Electronic)	978-1-61499-418-3
DOIs	https://doi.org/10.3233/978-1-61499-419-0-333
Publication status	Published - 18 Aug 2014

Access to Document

10.3233/978-1-61499-419-0-333

https://dl.acm.org/citation.cfm?id=3006709

Cite this

@inproceedings{fe67a2368ebf4325b8b83ab4a0645476,

title = "Argumentation accelerated reinforcement learning for cooperative multi-agent systems",

abstract = "Multi-Agent Learning is a complex problem, especially in real-time systems. We address this problem by introducing Argumentation Accelerated Reinforcement Learning (AARL), which provides a methodology for defining heuristics, represented by arguments, and incorporates these heuristics into Reinforcement Learning (RL) by using reward shaping. We define AARL via argumentation and prove that it can coordinate independent cooperative agents that have a shared goal but need to perform different actions. We test AARL empirically in a popular RL testbed, RoboCup Takeaway, and show that it significantly improves upon standard RL.",

author = "Yang Gao and Francesca Toni",

year = "2014",

month = aug,

day = "18",

doi = "10.3233/978-1-61499-419-0-333",

language = "English",

pages = "333--338",

booktitle = "ECAI'14 Proceedings of the Twenty-first European Conference on Artificial Intelligence",

publisher = "IOS Press",

}

TY - GEN

T1 - Argumentation accelerated reinforcement learning for cooperative multi-agent systems

AU - Gao, Yang

AU - Toni, Francesca

PY - 2014/8/18

Y1 - 2014/8/18

N2 - Multi-Agent Learning is a complex problem, especially in real-time systems. We address this problem by introducing Argumentation Accelerated Reinforcement Learning (AARL), which provides a methodology for defining heuristics, represented by arguments, and incorporates these heuristics into Reinforcement Learning (RL) by using reward shaping. We define AARL via argumentation and prove that it can coordinate independent cooperative agents that have a shared goal but need to perform different actions. We test AARL empirically in a popular RL testbed, RoboCup Takeaway, and show that it significantly improves upon standard RL.

AB - Multi-Agent Learning is a complex problem, especially in real-time systems. We address this problem by introducing Argumentation Accelerated Reinforcement Learning (AARL), which provides a methodology for defining heuristics, represented by arguments, and incorporates these heuristics into Reinforcement Learning (RL) by using reward shaping. We define AARL via argumentation and prove that it can coordinate independent cooperative agents that have a shared goal but need to perform different actions. We test AARL empirically in a popular RL testbed, RoboCup Takeaway, and show that it significantly improves upon standard RL.

U2 - 10.3233/978-1-61499-419-0-333

DO - 10.3233/978-1-61499-419-0-333

M3 - Conference contribution

SP - 333

EP - 338

BT - ECAI'14 Proceedings of the Twenty-first European Conference on Artificial Intelligence

PB - IOS Press

ER -