pith. sign in

arxiv: 2401.04934 · v1 · pith:QJQSIB7Xnew · submitted 2024-01-10 · 💻 cs.MA · cs.AI· cs.LG

Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey

classification 💻 cs.MA cs.AIcs.LG
keywords agentsdecentralizedfullycooperativelearningmaximizingmulti-agentreal-world
0
0 comments X
read the original abstract

Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world cooperative tasks, but restrictions of real-world applications may require training the agents in a fully decentralized manner. Due to the lack of information about other agents, it is challenging to derive algorithms that can converge to the optimal joint policy in a fully decentralized setting. Thus, this research area has not been thoroughly studied. In this paper, we seek to systematically review the fully decentralized methods in two settings: maximizing a shared reward of all agents and maximizing the sum of individual rewards of all agents, and discuss open questions and future research directions.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Learning to cooperate with emergent reputation via multi-agent reinforcement learning

    cs.GT 2026-06 unverdicted novelty 7.0

    COOPER is a distributed MARL method that learns emergent reputation assessment rules and policies from rewards, shown on donation and coin games in grid worlds with adaptation across co-players and networks.

  2. Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem

    cs.LG 2025-09 unverdicted novelty 5.0

    DAC models fully decentralized cooperative MARL as a context modeling problem, using latent variables for joint policies to fix non-stationarity in value updates and relative overgeneralization in value estimation.