Download - Evolving Agents in a Hostile Environment
![Page 1: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/1.jpg)
Evolving Agents in a Hostile Environment
Alex J. Berry
![Page 2: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/2.jpg)
Overview
Motivation Background The Approach Map Generation Evolutionary Algorithm Experiments
![Page 3: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/3.jpg)
Training First Responders
VEnOM Labs is developing a suite to train First Responders
Is the training effective? How can we make the training more
effective?
![Page 4: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/4.jpg)
![Page 5: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/5.jpg)
Goal
To develop a system to allow for friendly and hostile AI agents in the training environment.
To develop a system to create better agents for training First Responders.
![Page 6: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/6.jpg)
Simulation of Adaptive Agents in a Hostile Environment[HW95]
Thomas Haynes Simple Agents Mines and Energy Experiments
Single Agent, Static and Random Environment Multiple Agent, Static and Random Environment
![Page 7: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/7.jpg)
The Complicator
Aliases: Dr. T, Dr. Tauritz
Input: 2+2=4 Output:
0,45
%7
2)84)%42118798452((9303
162
![Page 8: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/8.jpg)
The Approach
Randomly Generated Grid Environment Three Types of Agents:
First Responders Terrorists Victims
Genetic Programming to Evolve the Agents
![Page 9: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/9.jpg)
Randomly Generated Maps
Any Dimension Percentage walls Bit Array to Hold the
Data
![Page 10: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/10.jpg)
Demo
![Page 11: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/11.jpg)
What’s an Agent to do?
Victims Move Randomly Remember Things Forget Things Survive
Terrorists Kill Victims Kill First Responders Lay Traps Disguise Themselves Not Get Caught
First Responders Help Victims Find and Disarm Traps Survive Catch Terrorists
![Page 12: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/12.jpg)
Evolutionary Algorithm
Two Agents to Evolve First Responder Terrorist
Two Competing Evolving Populations Genetic Programming for the Evolutionary
Implementation
![Page 13: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/13.jpg)
What An Individual Looks Like
Terminals Current Grid Location (C) Surrounding Grid Locations
(S) Rand (R)
Non-Terminals If-Then-Else
Threat And, Or, Not Victim, First Responder,
Terrorist, Trap Valid Move
Actions Save Kill Move Place Trap Remove Trap Not (Action) to invert an
Action
![Page 14: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/14.jpg)
Sample Individuals
Move
![Page 15: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/15.jpg)
Genetic Programming Evaluation
First Responder Victims Helped Terrorists Caught Traps Found Traps Removed Survival Amount of the Map
explored
Terrorist Kills using Traps Kills on Contact Effective Disguises Amount of Time
Survived
![Page 16: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/16.jpg)
Experiments
Static Environment Evolution Random Environment Evolution Varying Ratios of First Responders, Victims, and
Terrorists Evolving one Population at a Time
![Page 17: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/17.jpg)
Summary
Looking at agents operating in a hostile environment. First Responders, Terrorists, and Victims
Evolving first responders and terrorist using genetic programming techniques.
![Page 18: Evolving Agents in a Hostile Environment](https://reader035.vdocuments.mx/reader035/viewer/2022062517/56813c03550346895da56875/html5/thumbnails/18.jpg)
Future Work and Questions
Other Evolutionary Approaches LCS GP-LCS Hybrid
Integration into a 3D environment Playable Human Mode
Representations of Real Buildings Test effectiveness of adding this to Affective Intensity
Experiment Integration of other types of Traps and sensors to detect
those traps