Eavesdropping Opponent Agent Communication Using Deep Learning

We present a method for learning to interpret and understand foreign agent communication. Our approach is based on casting the contents of intercepted opponent agent communication to a bit-level representation and on training and employing deep convolutional neural networks for decoding the meaning of received messages. We empirically evaluate our method on real-world data acquired from the multi-agent domain of robotic soccer simulation, demonstrating the effectiveness and robustness of the learned decoding models.

[1]  Ian Frank,et al.  Soccer Server: A Tool for Research on Multiagent Systems , 1998, Appl. Artif. Intell..

[2]  Brendan J. Frey,et al.  Adaptive dropout for training deep neural networks , 2013, NIPS.

[3]  Luís Paulo Reis,et al.  An automatic approach to extract goal plans from soccer simulated matches , 2013, Soft Comput..

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[6]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[7]  Frieder Stolzenburg,et al.  Multiagent Matching Algorithms with and without Coach , 2006, J. Decis. Syst..

[8]  Manuela M. Veloso,et al.  Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork , 1999, Artif. Intell..

[9]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[10]  Peter Stone,et al.  Progress in Learning 3 vs. 2 Keepaway , 2003, RoboCup.

[11]  Nikos A. Vlassis,et al.  Non-communicative multi-robot coordination in dynamic environments , 2005, Robotics Auton. Syst..

[12]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[13]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[14]  Michael Wooldridge,et al.  Reasoning about rational agents , 2000, Intelligent robots and autonomous agents.

[15]  Hamidreza Chitsaz,et al.  The Fifth Robotic Soccer World Championships , 2002 .

[16]  Peter Stone,et al.  Keepaway Soccer: From Machine Learning Testbed to Benchmark , 2005, RoboCup.

[17]  Peter Stone,et al.  Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study , 2006, RoboCup.

[18]  Martin A. Riedmiller,et al.  Reinforcement learning for robot soccer , 2009, Auton. Robots.

[19]  Tuomas Sandholm,et al.  Safe and Nested Subgame Solving for Imperfect-Information Games , 2017, NIPS.

[20]  Martin A. Riedmiller,et al.  Learning a Partial Behavior for a Competitive Robotic Soccer Agent , 2006, Künstliche Intell..

[21]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .