paper-with-me

Papers

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel

2022-05-21 · Dianbo Liu, Vedant Shah, Oussama Boussif, Cristian Meo, Anirudh Goyal, Tianmin Shu, Michael Mozer, Nicolas Heess, Yoshua Bengio

In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. In this paper, we propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents' collective performance. To ensure that this facilitator does not become a centralized controller, agents are incentivized to reduce their dependence on the messages it conveys, and the messages can only influence the selection of a policy from a fixed set, not instantaneous actions given the policy. We demonstrate the strength of this architecture over existing baselines on several cooperative MARL environments.

📄 PDF Abstract BibTeX arXiv:2205.10607

Code (0)

등록된 구현이 없습니다.

Tasks

Intelligent CommunicationMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Adaptive Value Decomposition: Coordinating a Varying Number of Agents in Urban Systems

2026-02-10 · Yexin Li, Jinjin Guo, Haoyu Zhang, Yuhan Zhao 외 arxiv

Multi-agent reinforcement learning (MARL) provides a promising paradigm for coordinating multi-agent systems (MAS). However, most existing methods rely on restrictive assumptions, such as a fixed number of agents and ful…

Multi-agent Reinforcement Learning

A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning

2023-03-10 · Xinyi Zhang, Zhuo Chang, Hong Wu, Yang Li 외

Recently using machine learning (ML) based techniques to optimize modern database management systems has attracted intensive interest from both industry and academia. With an objective to tune a specific component of a D…

Thompson Sampling

Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning

2026-02-19 · Nikunj Gupta, James Zachary Hare, Jesse Milzman, Rajgopal Kannan 외 arxiv

Coordinating actions is the most fundamental form of cooperation in multi-agent reinforcement learning (MARL). Successful decentralized decision-making often depends not only on good individual actions, but on selecting …

Multi-agent Reinforcement Learning

Coordinated Multi-Agent Imitation Learning

2017-03-09 · ICML 2017 8 · Hoang M. Le, Yisong Yue, Peter Carr, Patrick Lucey

We study the problem of imitation learning from demonstrations of multiple coordinating agents. One key challenge in this setting is that learning a good model of coordination can be difficult, since coordination is ofte…

Imitation Learning

Integrated Intelligent and Predictive Control: A Multi-Agent Adaptive Type-2 Fuzzy Control Architecture

2019-08-28

We propose a novel two-layer multi-agent architecture aimed at efficient real-time control of large-scale and complex-dynamics systems. The proposed architecture integrates intelligent control approaches (which have a lo…

Model Predictive Control