litlas
Log inCreate account

Learning Multiagent Communication with Backpropagation

Authors: Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus - Conference on Neural Information Processing Systems, NeurIPS 2016 cited by 1,370

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.

Multi-AgentReinforcement Learning…Multi-Agent Reinforcement Learning: Independent versus Cooperative AgentsIntroduction toReinforcement LearningIntroduction to Reinforcement LearningAn Algorithm forDistributed…An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent SystemsConsensus andCooperation in Networke…Consensus and Cooperation in Networked Multi-Agent SystemsA Comprehensive Surveyof Multiagent…A Comprehensive Survey of Multiagent Reinforcement LearningLearning ofcommunication codes in…Learning of communication codes in multi-agent reinforcement learning problemCoordinating multi-agentreinforcement learning…Coordinating multi-agent reinforcement learning with limited communicationMazeBase: A Sandbox forLearning from GamesMazeBase: A Sandbox for Learning from GamesHuman-level controlthrough deep…Human-level control through deep reinforcement learningLearning to Communicateto Solve Riddles with…Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-NetworksMastering the game of Gowith deep neural…Mastering the game of Go with deep neural networks and tree searchMultiagent Cooperationand Competition with…Multiagent Cooperation and Competition with Deep Reinforcement LearningA Unified Game-TheoreticApproach to Multiagent…A Unified Game-Theoretic Approach to Multiagent Reinforcement LearningEmergence of GroundedCompositional Language…Emergence of Grounded Compositional Language in Multi-Agent PopulationsModeling Others usingOneself in Multi-Agent…Modeling Others using Oneself in Multi-Agent Reinforcement LearningLearning to Cooperate inDecentralized…Learning to Cooperate in Decentralized Multi-robot Exploration of Dynamic EnvironmentsValue-DecompositionNetworks For Cooperativ…Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team RewardStarCraftMicromanagement With…StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer LearningHuman-level performancein 3D multiplayer games…Human-level performance in 3D multiplayer games with population-based reinforcement learningA survey on multi-agentdeep reinforcement…A survey on multi-agent deep reinforcement learning: from the perspective of challenges and applicationsLearning multi-agentcommunication with…Learning multi-agent communication with double attentional deep reinforcement learningMulti-AgentReinforcement Learning…Multi-Agent Reinforcement Learning: A Selective Overview of Theories and AlgorithmsMulti-AgentReinforcement Learning…Multi-Agent Reinforcement Learning: A Review of Challenges and ApplicationsMulti-Agent IncentiveCommunication via…Multi-Agent Incentive Communication via Decentralized Teammate ModelingLearning MultiagentCommunication with…Learning Multiagent Communication with BackpropagationEarlier referencesFocus paperCiting papersOlderNewer

Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.