Learning Multiagent Communication with Backpropagation

2016-05-25 · NeurIPS 2016 12 · Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus

Many tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not altered during training. In this paper we explore a simple neural model, called CommNet, that uses continuous communication for fully cooperative tasks. The model consists of multiple agents and the communication between them is learned alongside their policy. We apply this model to a diverse set of tasks, demonstrating the ability of the agents to learn to communicate amongst themselves, yielding improved performance over non-communicative agents and baselines. In some cases, it is possible to interpret the language devised by the agents, revealing simple but effective strategies for solving the task at hand.

📄 PDF Abstract BibTeX arXiv:1605.07736

Code (9)

Coac/CommNet-BiCnet tf

MUmarJaved/MultiAgent-Distributed-Reinforcement-Learning tf

anonymous1234517/code tf

cts198859/deeprl_dist tf

cts198859/deeprl_network tf

dongchen06/macacc pytorch

facebookarchive/commnet torch

facebookresearch/CommNet torch

isp1tze/MAProj pytorch

R-MADDPG for Partially Observable Environments and Limited Communication

2020-02-16 · Rose E. Wang, Michael Everett, Jonathan P. How

There are several real-world tasks that would benefit from applying multiagent reinforcement learning (MARL) algorithms, including the coordination among self-driving cars. The real world has challenging conditions for m…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Self-Driving Cars

Deep Multiagent Reinforcement Learning: Challenges and Directions

2021-06-29 · Annie Wong, Thomas Bäck, Anna V. Kononova, Aske Plaat

This paper surveys the field of deep multiagent reinforcement learning. The combination of deep neural networks with reinforcement learning has gained increased traction in recent years and is slowly shifting the focus f…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Sociology

Efficient Offline Communication Policies for Factored Multiagent POMDPs

2011-12-01 · NeurIPS 2011 12 · João V. Messias, Matthijs Spaan, Pedro U. Lima

Factored Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs) form a powerful framework for multiagent planning under uncertainty, but optimal solutions require a rigid history-based policy represent…

Form

A Semi-Decentralized Approach to Multiagent Control

2026-03-12 · Mahdi Al-Husseini, Mykel J. Kochenderfer, Kyle H. Wray arxiv

We introduce an expressive framework and algorithms for the semi-decentralized control of cooperative agents in environments with communication uncertainty. Whereas semi-Markov control admits a distribution over time for…

Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph

2020-03-02 · Chuangchuang Sun, Macheng Shen, Jonathan P. How

The complexity of multiagent reinforcement learning (MARL) in multiagent systems increases exponentially with respect to the agent number. This scalability issue prevents MARL from being applied in large-scale multiagent…

Reinforcement Learning Reinforcement Learning (RL)