paper-with-me

Papers

Distributed Value Decomposition Networks with Networked Agents

2025-02-11 · Guilherme S. Varela, Alberto Sardinha, Francisco S. Melo

We investigate the problem of distributed training under partial observability, whereby cooperative multi-agent reinforcement learning agents (MARL) maximize the expected cumulative joint reward. We propose distributed value decomposition networks (DVDN) that generate a joint Q-function that factorizes into agent-wise Q-functions. Whereas the original value decomposition networks rely on centralized training, our approach is suitable for domains where centralized training is not possible and agents must learn by interacting with the physical environment in a decentralized manner while communicating with their peers. DVDN overcomes the need for centralized training by locally estimating the shared objective. We contribute with two innovative algorithms, DVDN and DVDN (GT), for the heterogeneous and homogeneous agents settings respectively. Empirically, both algorithms approximate the performance of value decomposition networks, in spite of the information loss during communication, as demonstrated in ten MARL tasks in three standard environments.

📄 PDF Abstract BibTeX arXiv:2502.07635

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Networked Agents in the Dark: Team Value Learning under Partial Observability

2025-01-15 · Guilherme S. Varela, Alberto Sardinha, Francisco S. Melo

We propose a novel cooperative multi-agent reinforcement learning (MARL) approach for networked agents. In contrast to previous methods that rely on complete state information or joint observations, our agents must learn…

Multi-agent Reinforcement Learning

Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes

2023-07-31 · Donghwan Lee, Han-Dong Lim, Do Wan Kim

The main goal of this paper is to investigate continuous-time distributed dynamic programming (DP) algorithms for networked multi-agent Markov decision problems (MAMDPs). In our study, we adopt a distributed multi-agent …

Distributed Optimization

Towards Resilience for Multi-Agent $QD$-Learning

2021-04-07 · Yijing Xie, Shaoshuai Mou, Shreyas Sundaram

This paper considers the multi-agent reinforcement learning (MARL) problem for a networked (peer-to-peer) system in the presence of Byzantine agents. We build on an existing distributed $Q$-learning algorithm, and allow …

AllMulti-agent Reinforcement LearningQ-Learning

Networked Signal and Information Processing

2022-10-25 · Stefan Vlaski, Soummya Kar, Ali H. Sayed, José M. F. Moura

The article reviews significant advances in networked signal and information processing, which have enabled in the last 25 years extending decision making and inference, optimization, control, and learning to the increas…

Decision MakingInference Optimization

Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design

2026-05-01 · Seyed Mohammad Azimi-Abarghouyi, Mehdi Bennis, Leandros Tassiulas arxiv

Federated learning (FL) is fundamentally a distributed optimization problem executed by communicating agents with local data, local computation, and partial system visibility. Once FL is viewed through that lens, hierarc…

Distributed OptimizationFederated Learning