Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
We study a new class of Markov games, (multi-player) zero-sum Markov Games with Networked separable interactions (zero-sum NMGs), to model the local interaction structure in non-cooperative multi-agent sequential decision-making. We define a zero-sum NMG as a model where the payoffs of the auxiliary...
Main Author: | Park, Chanwoo |
---|---|
Other Authors: | Ozdaglar, Asuman |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2024
|
Online Access: | https://hdl.handle.net/1721.1/153885 |
Similar Items
-
On Reinforcement Learning for Turn-based Zero-sum Markov Games
by: Shah, D, et al.
Published: (2021) -
Germ Warfare and the Zero-Sum Game
by: Abd Razak, Dzulkifli
Published: (1995) -
Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-player General-Sum Games
by: Anagnostides, Ioannis, et al.
Published: (2022) -
Zero-Sum Polymatrix Games: A Generalization of Minmax
by: Cai, Yang, et al.
Published: (2017) -
The complexity of Nash equilibria in multiplayer zero-sum games and coordination games
by: Cai, Yang, Ph. D. Massachusetts Institute of Technology
Published: (2011)