Dr. Kenneth Stanley February 6, 2006 CAP6938 Neuroevolution and Artificial Embryogeny NeuroEvolution of Augmenting Topologies (NEAT) Dr. Kenneth Stanley February 6, 2006

TWEANN Problems Reminder Competing conventions problem Topology matching problem Initial population topology randomization Defective starter genomes Unnecessarily high-dimensional search space Loss of innovative structures More complex can’t compete in the short run Need to protect innovation NEAT directly addresses these challenges

Solutions: NEAT Historical markings match up different structures Speciation Keeps incompatible networks apart Protects innovation Incremental growth from minimal structure, i.e. complexification Avoids searching in unnecessarily high-d space Makes finding high-d solutions possible

Genetic Encoding in NEAT

Topological Innovation

Link Weight Mutation A random number is added or subtracted from the current weight/parameter The number can be chosen from uniform, Gaussian (normal) or other distributions Continuous parameters work best if capped The probability of mutating a particular gene may be low or high, and is separate from the magnitude added Probabilities and mutation magnitudes have a significant effect

Link Weight Mutation in NEAT C++ randnum=randposneg()*randfloat()*power; if (mut_type==GAUSSIAN) { randchoice=randfloat(); if (randchoice>gausspoint) ((*curgene)->lnk)->weight+=randnum; else if (randchoice>coldgausspoint) ((*curgene)->lnk)->weight=randnum; } else if (mut_type==COLDGAUSSIAN) //Cap the weights at 3.0 if (((*curgene)->lnk)->weight > 3.0) ((*curgene)->lnk)->weight = 3.0; else if (((*curgene)->lnk)->weight < -3.0) ((*curgene)->lnk)->weight = -3.0;

Topology Matching Problem Problem arises from adding new genes Same gene may be in different positions Different genes may be in same positions

Biological Motivation New genes appeared over biological evolution as well Nature has a solution to still know which is which Process of aligning and matching genes is called synapsis Uses homology to align genes: “. . .Crossing over thus generates homologous recombination; that is, it occurs between 2 regions of DNA containing identical or nearly identical sequences.” (Watson et al. 1987)

Artificial Synapsys: Tracking Genes through Historical Markings The numbers tell exactly when in history particular topological features appeared, so now they can be matched up any time in the future. In other words, they reveal gene homology.

Matching up Genes

Second Component: Speciation Protects Innovation Originally used for multimodal function optimization (Mahfood 1995) Organisms grouped by similarity (compatibility) Fitness sharing (Goldberg 1987, Spears 1995): Organisms in a species share the reward of their fitness peak To facilitate this, NEAT needs A compatibility measure Clustering based on compatibility, for fitness sharing

Measuring Compatibility Possible in NEAT through historical markings 3 factors affect compatibility via historical markings on connection genes: Excess Disjoint Average Weight Distance W Compatibility distance

Clustering Into Species

Dynamic Compatibility Thresholding

Fitness Sharing: Assigning Offspring to Species

Third Component: Complexification from Minimal Structure Addresses initialization problem Search begins in minimal-topology space Lower-dimensional structures easily optimized Useful innovations eventually survive So search transitions into good part of higher-dim. space The ticket to high-dimensional space

NEAT Performed Well on Double Pole Balancing Without Velocity Inputs

DPNV Solutions Are Compact

Harder DPNV (0.3m short pole) solution

Visualizing Speciation

Next Class: More NEAT Implementation issues Where NEAT can be changed Areas for advancement Issues in applying NEAT (e.g. sensors and outputs) Evolving a Roving Eye for Go by Kenneth O. Stanley and Risto Miikkulainen (2004) Neuroevolution of an Automobile Crash Warning System by Kenneth O. Stanley and Risto Miikkulainen (2005) Homework due 2/15/05: Working domain and phenotype code. Turn in summary, code, and examples demonstrating how it works.

Project Milestones (25% of grade) 2/6: Initial proposal and project description 2/15: Domain and phenotype code and examples 2/27: Genes and Genotype to Phenotype mapping 3/8: Genetic operators all working 3/27: Population level and main loop working 4/10: Final project and presentation due (75% of grade)