1 / 12

Nexus: An agent based simulation of Irregular warfare

Nexus: An agent based simulation of Irregular warfare. Deborah Duong Ph.D. OSD/PA&E Simulation Analysis Center. Applying the VV&A Framework. Already used on Classified Scenarios

feng
Download Presentation

Nexus: An agent based simulation of Irregular warfare

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Nexus: An agent based simulation of Irregular warfare Deborah Duong Ph.D. OSD/PA&E Simulation Analysis Center

  2. Applying the VV&A Framework • Already used on Classified Scenarios • This VV&A will be done on proposed application to Operation Pacific Breeze Scenario (same scenario as Pythagoras COIN) • Presented in honor of Gandhi’s Birthday October 2, father of Nonviolent Revolution

  3. Nexus: An Intelligent Agent Simulation of Irregular Warfare • One agent per every relevant social group: whether groups overlap or contain each other does not matter. • Each agent has a “group mind” (or you can say… it’s the leader’s mind… ). • This group mind is a neural network, used to compute group support

  4. Nexus Simulation Loop • All groups compute their support for all other groups • Group A computes support for group B, with neural net, based on: • the past actions of group B • what other groups group B supports • how close group A is in ideology to group B • All groups make public declarations of support. • There is a hook for adding “believed support” if it differs from public declarations. • Groups modify their neural nets according to their new beliefs of public support. • Groups act based on CONOPS • Re-compute support, etc.

  5. Each Agent Mind is a Boltzmann Machine Neural Network

  6. The Boltzmann Machine • A Constraint Satisfaction Neural Network • Nodes may represent states of the world • Links may represent how much evidence of one state supports evidence of the other state • Stochastic: Uses Simulated Annealing • Nodes are turned on randomly at first • Each node computes its activation based on (activation of nodes linked to it X weight at synapse) • Represents a Paradigm of consonant states • Nodes compute activation over and over until all converge on a steady state • Settled upon state represent an internally consistent set of evidence, and a consensus of the evidence on the state. • Can represent a paradigm shift.

  7. Example: The Necker Cube

  8. Why is a Constraint Satisfaction Neural Network appropriate for the Marine Corps study? • Marine Corps study is based on the Narrative Paradigm • Identity important • My life is a coherent story, based on past experiences • Narrative Paradigm is part of Interpretive Social Science Paradigm • Constraint Satisfaction Neural Networks simulate Interpretive Social Science • Duong and Grefenstette, Thagard, and Sallach used them

  9. How do Constraint Satisfacton Neural Networks model Identity? • They model cognitive dissonance • Direct evidence may be against a fact, like “Smoking is good for you” or “Bush orchestrated 9/11” • However, if you are a smoker or a terrorist, you minimize direct evidence, and may believe false ideas because they make sense with the rest of your beliefs • Pride would cause smokers to minimize the evidence to rationalize their actions • The sets of evidence that are true are Paradigms of beliefs to base identity on

  10. Architecture of Nexus Neural Networks • Columns are social groups • First Row: Support Nodes • Second Row: Trust Nodes • Third Row on: Blame Nodes for Historical Events • One event per row • In order, bottom are future events • Evidence Node • Court-type “Proof” they’ve witnessed

  11. Agent’s Minds act according to the Narrative Paradigm • Agents seek a coherent picture of events • Agents may reinterpret the blame for events in the past depending on present beliefs • Agents choose alliances according to coherent picture • Coherence includes consonance with historical events, in an ongoing story • Data fits nicely into minds • “Bubble Data” as an ideological input into trust nodes • Saliance Data and present orientations as initial Support levels • Historical Event Data in Input and Blame Nodes • “Shore or Sea” Data as future events

  12. Narrative Paradigm is good for Irregular warfare • In emphasizing trust, one can simulate breaking of trust between groups • for example, Insurgents may incite Rodney King incidents, make videos of it and distribute it. Govt agents would be forced to prosecute police, separating police from government • Groups can represent countries and Gandhi type protests can represent actions that cause them to try to keep ideologically correct.

More Related