CAP6938 Neuroevolution and Developmental Encoding Realtime NEAT

1
CAP6938Neuroevolution and Developmental
EncodingReal-time NEAT

• Dr. Kenneth Stanley
• October 18, 2006

2
Generations May Not Always Be Appropriate

• When a population is evaluated simultaneously
• Many are observable at the same time
• Therefore, entire population would change at once
• A sudden change is incongruous, highly noticeable
• When a human interacts with one individual at a
  time
• Want things to improve constantly

3
Steady State GA One Individual Is Replaced at a
Time

• Start by evaluating entire first generation
• Then continually pick one to remove, replace it
  with child of the best

Start Evaluate All
2) Create offpsring from good parents
Repeat
3) Replace removed individual
1) Remove poor individual
4
Steady State During Simultaneous Evaluation
Similar but not Identical

• Several new issues when evolution is real-time
• Evaluation is asynchronous
• When to replace?
• How to assign fitness?
• How to display changes

5
Regular NEAT Introduces Additional Challenges for
Real Time

• Speciation equations based on generations
• No remove worst operation defined in algorithm
• Dynamic compatibility thresholding assumes
  generations

6
Speciation Equations Based on Generations
7
How to Remove the Worst?

• No such operation in generational NEAT
• Worst often may often be a new species
• Removing it would destroy protection of
  innovation
• Loss of regular NEAT dynamics

8
Dynamic Compatibility Thresholding Assumes A Next
Generation
9
Real-time NEAT Addresses Both the Steady State
and Simultaneity Issues

• Real-time speciation
• Simultaneous and asynchronous evaluation
• Steady state replacement
• Fast enough to change while a game is played
• Equivalent dynamics to regular NEAT

10
Main Loop (Non-Generational)
11
Choosing the Parent Species
12
Finally How Many Ticks Between Replacements?

• Intuitions
• The more often replacement occurs, the fewer are
  eligible
• The larger the population, the more are eligible
• The high the age of maturity, the fewer are
  eligible

13
rtNEAT Is Implemented In NERO

• Download at http//nerogame.org
• rtNEAT source available
• Simulated demos have public appeal
• Over 70,000 downloads
• Appeared on Slashdot
• Best Paper Award in Computational Intelligence
  and Games
• Independent Games Festival Best Student Game
  Award
• rtNEAT licensed
• Worldwide media coverage

14
Media Coverage
15
Media Coverage
16
NERO NeuroEvolving Robotic Operatives

• NPCs improve in real time as game is played
• Player can train AI for goal and style of play
• Each AI Unit Has Unique NN

17
NERO Battle Mode

• After training, evolved behaviors are saved
• Player assembles team of trained agents
• Team is tested in battle against opponents team

18
NERO Training The Factory

• Reduces noise during evaluation
• All evaluations start out similarly
• Robot bodies produced by factory
• Each body sent back to factory to respawn
• Bodies retain their NN unless chosen for
  replacement
• NNs have different ages
• Fitness is diminishing average of spawn trials

19
NERO Inputs and Outputs
20
Enemy/Friend Radars
21
Enemy On-Target Sensor
22
Object Rangefinder Sensors
23
Enemy Line-of-Fire Sensors
24
Further Applications?

• New kinds of games
• New kinds of AI in games
• New kinds of real-time simulations
• Training applications
• Interactive steady-state evolution

25
Next Topic Improving the neural model

• Adaptive neural networks
• Change over a lifetime
• Leaky integrator neurons and CTRNN

Evolutionary Robots with On-line
Self-Organization and Behavioral Fitness by Dario
Floreano and Joseba Urzelai (2000)Evolving
Adaptive Neural Networks with and Without
Adaptive Synapses by Kenneth O. Stanley, Bobby D.
Bryant, and Risto Miikkulainen (2003)