English
Related papers

Related papers: Multi-Agent MDP Homomorphic Networks

200 papers

We present a principled and efficient planning algorithm for collaborative multiagent dynamical systems. All computation, during both the planning and the execution phases, is distributed among the agents; each agent only needs to model and…

Artificial Intelligence · Computer Science 2013-01-07 Carlos E. Guestrin , Geoffrey Gordon

This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep…

Machine Learning · Computer Science 2021-01-21 Elise van der Pol , Daniel E. Worrall , Herke van Hoof , Frans A. Oliehoek , Max Welling

In multi-agent reinforcement learning, centralized training with decentralized execution (CTDE) methods typically assume that agents make decisions based on their local observations independently, which may not lead to a correlated joint…

Multiagent Systems · Computer Science 2024-12-16 Zhiyuan Li , Wenshuai Zhao , Lijun Wu , Joni Pajarinen

We consider a cooperative multi-agent system consisting of a team of agents with decentralized information. Our focus is on the design of symmetric (i.e. identical) strategies for the agents in order to optimize a finite horizon team…

Optimization and Control · Mathematics 2023-07-17 Sagar Sudhakara , Ashutosh Nayyar

Consider a multi-agent system in a dynamic and uncertain environment. Each agent's local decision problem is modeled as a Markov decision process (MDP) and agents must coordinate on a joint action in each period, which provides a reward to…

Computer Science and Game Theory · Computer Science 2012-07-02 Ruggiero Cavallo , David C. Parkes , Satinder Singh

We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model. The framework extends the multi-agent learning…

Artificial Intelligence · Computer Science 2017-12-25 Saurabh Kumar , Pararth Shah , Dilek Hakkani-Tur , Larry Heck

Many multi-agent systems in practice are decentralized and have dynamically varying dependencies. There has been a lack of attempts in the literature to analyze these systems theoretically. In this paper, we propose and theoretically…

Machine Learning · Computer Science 2024-06-12 Alex DeWeese , Guannan Qu

We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to…

Multiagent Systems · Computer Science 2021-04-26 Alex Tong Lin , Mark J. Debord , Katia Estabridis , Gary Hewer , Guido Montufar , Stanley Osher

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 framework where…

Systems and Control · Electrical Eng. & Systems 2024-06-14 Donghwan Lee , Han-Dong Lim , Do Wan Kim

Multi-agent planning under stochastic dynamics is usually formalised using decentralized (partially observable) Markov decision processes ( MDPs) and reachability or expected reward specifications. In this paper, we propose a different…

Logic in Computer Science · Computer Science 2025-02-20 Francesco Pontiggia , Filip Macák , Roman Andriushchenko , Michele Chiari , Milan Češka

In multi-agent reinforcement learning, a commonly considered paradigm is centralized training with decentralized execution. However, in this framework, decentralized execution restricts the development of coordinated policies due to the…

Multiagent Systems · Computer Science 2024-12-30 Wenzhe Fan , Zishun Yu , Chengdong Ma , Changye Li , Yaodong Yang , Xinhua Zhang

We study a decentralized dispatch coordination problem in a multi-agent supply chain setting with shared logistics capacity. We propose symmetric (identical) dispatch strategies for all agents, enabling efficient coordination without…

Multiagent Systems · Computer Science 2025-04-29 Sagar Sudhakara

In the distributed optimization problem for a multi-agent system, each agent knows a local function and must find a minimizer of the sum of all agents' local functions by performing a combination of local gradient evaluations and…

Optimization and Control · Mathematics 2022-06-16 Bryan Van Scoy , Laurent Lessard

The paper considers a class of multi-agent Markov decision processes (MDPs), in which the network agents respond differently (as manifested by the instantaneous one-stage random costs) to a global controlled state and the control actions of…

Machine Learning · Statistics 2015-06-04 Soummya Kar , Jose' M. F. Moura , H. Vincent Poor

A number of prototypical optimization problems in multi-agent systems (e.g., task allocation and network load-sharing) exhibit a highly local structure: that is, each agent's decision variables are only directly coupled to few other agent's…

Multiagent Systems · Computer Science 2020-03-04 Robin Brown , Federico Rossi , Kiril Solovey , Michael T. Wolf , Marco Pavone

Current approaches to multi-agent cooperation rely heavily on centralized mechanisms or explicit communication protocols to ensure convergence. This paper studies the problem of distributed multi-agent learning without resorting to…

Multiagent Systems · Computer Science 2025-08-19 Caroline Wang , Ishan Durugkar , Elad Liebman , Peter Stone

Multi-agent reinforcement learning has emerged as a powerful framework for enabling agents to learn complex, coordinated behaviors but faces persistent challenges regarding its generalization, scalability and sample efficiency. Recent…

Robotics · Computer Science 2025-04-28 Nikolaos Bousias , Stefanos Pertigkiozoglou , Kostas Daniilidis , George Pappas

The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems. Since macro-actions last for stochastic…

Artificial Intelligence · Computer Science 2019-05-30 Kunal Menda , Yi-Chun Chen , Justin Grana , James W. Bono , Brendan D. Tracey , Mykel J. Kochenderfer , David Wolpert

Reinforcement learning agents must painstakingly learn through trial and error what sets of state-action pairs are value equivalent -- requiring an often prohibitively large amount of environment experience. MDP homomorphisms have been…

In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We…

Artificial Intelligence · Computer Science 2022-05-12 Niall Creech , Natalia Criado Pacheco , Simon Miles
‹ Prev 1 2 3 10 Next ›