Theoretical Principles of Multi-Agent Reinforcement Learning for Coalitional Bargaining games

Lucia Cipolina-Kun; Ignacio Carlucho; Stephen Mak; Kalesha Bullard; Vahid Yazdanpanah; Enrico H. Gerding; Sebastian Stein

Theoretical Principles of Multi-Agent Reinforcement Learning for Coalitional Bargaining games

Lucia Cipolina-Kun
, Ignacio Carlucho
, Stephen Mak
, Kalesha Bullard
, Vahid Yazdanpanah
, Enrico H. Gerding
, Sebastian Stein

Research output: Contribution to conference › Paper › peer-review

Abstract

The rising focus on employing multi-agent reinforcement learning (MARL) in coalitional bargaining games (CBG) has exposed a need for robust theoretical principles linking the two. To address this, we explore the relationship between CBG and MARL within the context of stochastic games, and show that under some assumptions, CBG are a subclass of sequential stochastic games. Out work is a step forward in the reproducibility and generalization of MARL results to CBG.

Original language	English
Publication status	Published - 5 May 2023
Event	11th International Conference on Learning Representations 2023: 1st Tiny Papers Workshop - Kigali, Rwanda Duration: 1 May 2023 → 5 May 2023 https://iclr.cc/Conferences/2023

Conference

Conference	11th International Conference on Learning Representations 2023
Abbreviated title	ICLR 2023
Country/Territory	Rwanda
City	Kigali
Period	1/05/23 → 5/05/23
Internet address	https://iclr.cc/Conferences/2023

ASJC Scopus subject areas

Linguistics and Language
Language and Linguistics
Computer Science Applications
Education

Cite this

@conference{d1e55ae830894bbf8d945a19b22bfe82,

title = "Theoretical Principles of Multi-Agent Reinforcement Learning for Coalitional Bargaining games",

abstract = "The rising focus on employing multi-agent reinforcement learning (MARL) in coalitional bargaining games (CBG) has exposed a need for robust theoretical principles linking the two. To address this, we explore the relationship between CBG and MARL within the context of stochastic games, and show that under some assumptions, CBG are a subclass of sequential stochastic games. Out work is a step forward in the reproducibility and generalization of MARL results to CBG.",

author = "Lucia Cipolina-Kun and Ignacio Carlucho and Stephen Mak and Kalesha Bullard and Vahid Yazdanpanah and Gerding, \{Enrico H.\} and Sebastian Stein",

note = "Publisher Copyright: {\textcopyright} 2023 1st Tiny Papers Track at ICLR 2023 - Tiny Papers @ ICLR 2023. All rights reserved.; 11th International Conference on Learning Representations 2023 : 1st Tiny Papers Workshop, ICLR 2023 ; Conference date: 01-05-2023 Through 05-05-2023",

year = "2023",

month = may,

day = "5",

language = "English",

url = "https://iclr.cc/Conferences/2023",

}

TY - CONF

T1 - Theoretical Principles of Multi-Agent Reinforcement Learning for Coalitional Bargaining games

AU - Cipolina-Kun, Lucia

AU - Carlucho, Ignacio

AU - Mak, Stephen

AU - Bullard, Kalesha

AU - Yazdanpanah, Vahid

AU - Gerding, Enrico H.

AU - Stein, Sebastian

PY - 2023/5/5

Y1 - 2023/5/5

N2 - The rising focus on employing multi-agent reinforcement learning (MARL) in coalitional bargaining games (CBG) has exposed a need for robust theoretical principles linking the two. To address this, we explore the relationship between CBG and MARL within the context of stochastic games, and show that under some assumptions, CBG are a subclass of sequential stochastic games. Out work is a step forward in the reproducibility and generalization of MARL results to CBG.

AB - The rising focus on employing multi-agent reinforcement learning (MARL) in coalitional bargaining games (CBG) has exposed a need for robust theoretical principles linking the two. To address this, we explore the relationship between CBG and MARL within the context of stochastic games, and show that under some assumptions, CBG are a subclass of sequential stochastic games. Out work is a step forward in the reproducibility and generalization of MARL results to CBG.

UR - https://www.scopus.com/pages/publications/105026749736

M3 - Paper

AN - SCOPUS:105026749736

T2 - 11th International Conference on Learning Representations 2023

Y2 - 1 May 2023 through 5 May 2023

ER -

Theoretical Principles of Multi-Agent Reinforcement Learning for Coalitional Bargaining games

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this