New version page

UCF CAP 6938 - Neuroevolution and Developmental Encoding

Upgrade to remove ads
Upgrade to remove ads
Unformatted text preview:

CAP6938 Neuroevolution and Developmental Encoding Working with NEATExploiting SpeciationCrossover IssueLook Out for BugsNetwork ActivationReal-time EvolutionYour Genes May Have Extra FieldsImportant MethodsDevelopmental Encoding and Non-neural NEATSensors Must Be Chosen WiselyNoisy EvaluationSaving and LoadingModularity Means Future Expansion (and maybe other users)Too Much Scope = Too Much RopeNext Class: Developmental EncodingCAP6938Neuroevolution and Developmental EncodingWorking with NEAT Dr. Kenneth StanleySeptember 27, 2006Exploiting Speciation•Keep a list of species with increasing ID’s•Species elitism: duplicate the species champs in the next generation–Only if species is above size 4 or 5–Irrelevant in rtNEAT•Stagnation Detection–Track generations since last improvement for each species–Drop fitnesses of stagnant species to near 0Crossover Issue•Two different connections can end up connecting the same nodes–Maybe disallow59Look Out for Bugs•Gene pointing to nodes that aren’t in Gemome•Gene innovation numbers out of order•Node innovation numbers out of order•Duplicate genes•May want to check for these situations after major operations during debugging•See Genome::verify() in NEAT C++•Can check whole population in a loopNetwork Activation•Use standard arbitrary-topology activation•(Lecture 3)•Do not activate in layers!Real-time Evolution•If all your agents are evaluated simultaneously, rtNEAT may be more appropriate•rtNEAT produces and replaces one individual at a time (no generations)•See “REAL-TIME NEUROEVOLUTION IN THE NERO VIDEO GAME ” on my homepage•Also see NERO•rtNEAT source availableYour Genes May Have Extra Fields•Time constants in nodes•Activation function in nodes•Learning parameters in connections•You can have whatever you want, whatever you are evolving•Should extra params affect compatibility?•Remember, more fields means more possibilities, but also more dimensionsWcNDcNEc321Important Methods•Crossover: mate_multipoint and mate_multipoint_avg•Mutation: mutate_add_connection, mutate_link_weights, mutate_enable_bits, other?•Special Genomes Operations: duplicate, compare (getting the delta for compatibility distance)•reproduce (inside Species)•epoch (inside Population)•Remember: http://www.freshraisins.com/neatdoc/files/genetics-cpp.htmlDevelopmental Encoding and Non-neural NEAT•Your genes may not map directly to pieces of structure•However, genes can still be marked with historical markings and complexification can still occur•Need a standard starting structureSensors Must Be Chosen WiselyNoisy Evaluation•Randomness in an environment can cause evaluation to be inconsistent•For example, in a game of chance•Same individual can receive different fitness on different trials•Causes confusion for evolution•Not always fatal, but merits attention•Maybe give all individuals in same generation same evaluation sequenceSaving and Loading•Genomes/Populations should be savable and loadable•Important for debugging•Very disappointing to lose a good thing forever•Some people use standards like XML/* Species #3 : (Size 5) (AF 6.03094) (Age 29) *//* Organism #0 Fitness: 8.77021 Error: 1.03855 */genomestart 0trait 1 0.1 0 0 0 0 0 0 0trait 2 0.2 0 0 0 1 0 0.21903 0trait 3 0.65 0.110145 0 0 0 0 0 0node 1 3 1 3node 2 3 1 1node 3 3 1 1node 4 1 0 2node 9 1 0 0node 86 1 0 0gene 3 1 4 -0.798127 0 1 -0.798127 1gene 3 2 4 3 0 2 3 1gene 2 3 4 -3 0 3 -3 1gene 2 3 9 0.505339 0 12 0.505339 1gene 1 9 4 1.02135 0 13 1.02135 1gene 1 1 9 -3 0 95 -3 1gene 1 2 9 2.28649 0 266 2.28649 0gene 1 2 86 -1.22499 0 281 -1.22499 1gene 1 86 9 1.72795 0 282 1.72795 1genomeend 0/* Organism #1 Fitness: 5.37326 Error: 1.68197 */genomestart 1trait 1 0.1 0 0 0 0 0 0 0trait 2 0.2 0 0 0 1 0 0.21903 0trait 3 0.65 0.110145 0 0 0 0 0 0node 1 3 1 3node 2 3 1 1node 3 3 1 1node 4 1 0 2node 9 1 0 0Modularity Means Future Expansion (and maybe other users)•Think about what you might want to do someday–Add new parameters to nodes?–Add new parameters to links?–Change the mapping?–Change platforms?–Completely different experiments?–More visualization?–Change phenotype?–Change genetyoe?Too Much Scope = Too Much Rope•Go for proof of concept•What feature matters least?•If nothing works what could be a prerequisite task?•Incremental evolution strategiesNext Class: Developmental Encoding•The power of reuse•Prior work•Biological underpinnings•The futureA Taxonomy for Artificial Embryogeny by Kenneth O. Stanley and Risto Miikkulainen


View Full Document
Download Neuroevolution and Developmental Encoding
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Neuroevolution and Developmental Encoding and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Neuroevolution and Developmental Encoding 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?