English
Related papers

Related papers: Cooperative Actor-Critic via TD Error Aggregation

200 papers

Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in non-communicating scenarios where each agent's intent (e.g. goal) is unobservable to the others. In particular, finding time efficient paths…

Multiagent Systems · Computer Science 2016-09-29 Yu Fan Chen , Miao Liu , Michael Everett , Jonathan P. How

In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required. The rather general and widely applicable control setting, where each cooperation…

Multiagent Systems · Computer Science 2019-10-30 Florian Köpf , Samuel Tesfazgi , Michael Flad , Sören Hohmann

We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each…

Multiagent Systems · Computer Science 2021-11-02 Kuo Li , Qing-Shan Jia

Actor-critic (AC) algorithms have been widely adopted in decentralized multi-agent systems to learn the optimal joint control policy. However, existing decentralized AC algorithms either do not preserve the privacy of agents or are not…

Machine Learning · Computer Science 2022-02-04 Ziyi Chen , Yi Zhou , Rongrong Chen , Shaofeng Zou

This work develops a fully decentralized multi-agent algorithm for policy evaluation. The proposed scheme can be applied to two distinct scenarios. In the first scenario, a collection of agents have distinct datasets gathered following…

Machine Learning · Computer Science 2019-08-13 Lucas Cassano , Kun Yuan , Ali H. Sayed

Data collecting agents in large networks, such as the electric power system, need to share information (measurements) for estimating the system state in a distributed manner. However, privacy concerns may limit or prevent this exchange…

Information Theory · Computer Science 2015-10-28 E. Veronica Belmega , Lalitha Sankar , H. Vincent Poor

We show that, in large population games, decentralized information aggregation generically corrects for individual-level biases. This establishes a new testable aggregate efficiency benchmark where the behavior of boundedly rational agents…

Theoretical Economics · Economics 2026-02-17 Florian Mudekereza

Information exchange in multi-agent systems improves the cooperation among agents, especially in partially observable settings. In the real world, communication is often carried out over imperfect channels. This requires agents to handle…

Multiagent Systems · Computer Science 2023-11-28 Jannis Weil , Gizem Ekinci , Heinz Koeppl , Tobias Meuser

We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment,…

Machine Learning · Computer Science 2020-03-17 Ryan Lowe , Yi Wu , Aviv Tamar , Jean Harb , Pieter Abbeel , Igor Mordatch

We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from…

We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federated multi-agent system. Each AI agent and critic has access to classical machine learning or generative AI foundation models. The…

Artificial Intelligence · Computer Science 2026-04-02 Syed Eqbal Alam , Zhan Shu

Learning cooperative policies for multi-agent systems is often challenged by partial observability and a lack of coordination. In some settings, the structure of a problem allows a distributed solution with limited communication. Here, we…

Systems and Control · Computer Science 2017-08-01 Roel Dobbe , David Fridovich-Keil , Claire Tomlin

Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In…

Machine Learning · Computer Science 2021-12-06 Xueguang Lyu , Yuchen Xiao , Brett Daley , Christopher Amato

We study multi-agent reinforcement learning in the setting of episodic Markov decision processes, where multiple agents cooperate via communication through a central server. We propose a provably efficient algorithm based on value iteration…

Machine Learning · Computer Science 2023-06-27 Yifei Min , Jiafan He , Tianhao Wang , Quanquan Gu

The finite-time convergence of off-policy TD learning has been comprehensively studied recently. However, such a type of convergence has not been well established for off-policy TD learning in the multi-agent setting, which covers broader…

Machine Learning · Computer Science 2021-03-25 Ziyi Chen , Yi Zhou , Rongrong Chen

There are many AI tasks involving multiple interacting agents where agents should learn to cooperate and collaborate to effectively perform the task. Here we develop and evaluate various multi-agent protocols to train agents to collaborate…

Multiagent Systems · Computer Science 2019-07-02 Niranjan Balachandar , Justin Dieter , Govardana Sachithanandam Ramachandran

We propose an efficient multi-agent reinforcement learning approach to derive equilibrium strategies for multi-agents who are participating in a Markov game. Mainly, we are focused on obtaining decentralized policies for agents to maximize…

Multiagent Systems · Computer Science 2018-10-23 Heechang Ryu , Hayong Shin , Jinkyoo Park

We consider a task-effective quantization problem that arises when multiple agents are controlled via a centralized controller (CC). While agents have to communicate their observations to the CC for decision-making, the bit-budgeted…

Information Theory · Computer Science 2023-01-05 Arsham Mostaani , Thang X. Vu , Symeon Chatzinotas , Bjorn Ottersten

In this work we derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints, a regression problem. Agents employ the recently proposed ACTC…

Machine Learning · Computer Science 2025-04-25 Marco Carpentiero , Vincenzo Matta , Ali H. Sayed

One of the preeminent obstacles to scaling multi-agent reinforcement learning to large numbers of agents is assigning credit to individual agents' actions. In this paper, we address this credit assignment problem with an approach that we…

Machine Learning · Computer Science 2021-12-24 Benjamin Freed , Aditya Kapoor , Ian Abraham , Jeff Schneider , Howie Choset