arXiv (Cornell University) · 2016 · 86 citations · 35 references
ComputingCommunicationComputer ScienceArtificial IntelligenceDistributed SystemsMachine LearningDeep LearningDistributed CoordinationMulti-agent SystemsNeural NetworksReinforcement LearningTeam LearningCommunication LearningCommunication Protocol DesignCommunication ProtocolsDeep Reinforcement LearningLearned Communication ProtocolsMulti-agent LearningQ-learningRecurrent Neural Networks
We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks. In these tasks, the agents are not given any pre-designed communication protocol. Therefore, in order to successfully communicate, they must first automatically develop and agree upon their own communication protocol. We present empirical results on two multi-agent learning problems based on well-known riddles, demonstrating that DDRQN can successfully solve such tasks and discover elegant communication protocols to do so. To our knowledge, this is the first time deep reinforcement learning has succeeded in learning communication protocols. In addition, we present ablation experiments that confirm that each of the main components of the DDRQN architecture are critical to its success.
35
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations
Consensus and Cooperation in Networked Multi-Agent Systems
Reza Olfati‐Saber, J.A. Fax, Richard M. Murray · Proceedings of the IEEE · 2007 · 10.3K citations