class NEAT::Controller

Controller for all operations of RubyNEAT¶ ↑

This object contains all the specifications and details for
evolving and evaluation of the RubyNEAT system.  It is 
a type of "World", if you will, for the entire enterprise.

Your application shall only have one Controller.

Attributes

compare_func[RW]

Compare function for fitness Cost function for integrating in the cost to the fitness scalar.

cost_func[RW]

Compare function for fitness Cost function for integrating in the cost to the fitness scalar.

end_run_func[RW]

End run function to call at the end of each generational run Also #report_hook to dump reports for the user, etc.

evaluator[RW]

evaluator_class[RW]

evolver[RW]

evolver_class[RW]

expressor[RW]

expressor_class[RW]

fitness_func[RW]

Fitness function that Critters shall be rated on.

generation_num[R]

Current generation count

glob_innov_num[R]

global innovation number

log[R]

Logger object for all of RubyNEAT

neural_hidden[RW]

Class map of named input and output neurons (each critter will have instantiations of these) name: InputNeuralClass (usually InputNeuron)

neural_inputs[RW]

Class map of named input and output neurons (each critter will have instantiations of these) name: InputNeuralClass (usually InputNeuron)

neural_outputs[RW]

Class map of named input and output neurons (each critter will have instantiations of these) name: InputNeuralClass (usually InputNeuron)

neuron_catalog[RW]

catalog of neurons classes to use { weight => nclass, … }

parms[RW]

Parameters for evolution (NeatParameters)

population[R]

population object and class specification

population_class[R]

population object and class specification

population_history[R]

population object and class specification

query_func[RW]

Query function that Critters shall call.

recurrence_func[RW]

Recurrence function that Critters will yield to.

report_hook[RW]

End run function to call at the end of each generational run Also #report_hook to dump reports for the user, etc.

seq_num[R]

current sequence number being evaluated

stop_on_fit_func[RW]

Compare function for fitness Cost function for integrating in the cost to the fitness scalar.

verbosity[RW]

Global verbosity level:

1 - normal (the default)
2 - really verbose
3 - maximally verbose

Use in conjunction with log.debug

Public Class Methods

new(neural_inputs: nil, neural_outputs: nil, neural_hidden: nil, parameters: NeatSettings.new, &block) click to toggle source

#neural_inputs – array of input classes
#neural_outputs – array of output classes
parameters – NeatParameters object, or a path to a YAML file to create this.

Calls superclass method NEAT::NeatOb.new

# File lib/rubyneat/rubyneat.rb, line 334
def initialize(neural_inputs: nil,
               neural_outputs: nil,
               neural_hidden: nil,
               parameters: NeatSettings.new,
                  &block)
  super(self)
  @verbosity = 1
  @glob_innov_num = 0
  @gaussian = Distribution::Normal.rng
  @population_history = []
  @evolver = Evolver.new self
  @expressor = Expressor.new self

  @neuron_catalog = Neuron::neuron_types.clone
  @neural_inputs  = neural_inputs
  @neural_outputs = neural_outputs
  @neural_hidden  = neural_hidden

  # Default classes for population and operators, etc.
  @population_class = NEAT::Population
  @evaluator_class = NEAT::Evaluator
  @expressor_class = NEAT::Expressor
  @evolver_class = NEAT::Evolver

  # Handle the parameters parameter. :-)
  @parms = unless parameters.kind_of? String
             parameters
           else # load it from a file
             open(parameters, 'r') { |fd| YAML::load fd.read }
           end
  block.(self) unless block.nil?
end

Public Instance Methods

gaussian() click to toggle source

# File lib/rubyneat/rubyneat.rb, line 368
def gaussian ; @gaussian.() ; end

new_innovation() click to toggle source

# File lib/rubyneat/rubyneat.rb, line 367
def new_innovation ; @glob_innov_num += 1; end

run() click to toggle source

Run this evolution.

# File lib/rubyneat/rubyneat.rb, line 371
def run
  pre_run_initialize
  (1..@parms.max_generations).each do |gen_number|
    @generation_num = gen_number
    @population_history << unless @population.nil?
                             @population
                           else
                             @population = @population_class.new(self)
                           end
    @population_history.shift unless @population_history.size <= @parms.max_population_history
    @population.mutate!
    @population.express!

    ## Evaluate population
    @evaluator.ready_for_evaluation @population
    (@parms.start_sequence_at .. @parms.end_sequence_at).each do |snum|
      @seq_num = snum
      @population.evaluate!
    end

    @population.analyze!
    @population.speciate!

    $log.debug @population.dump_s unless @verbosity < 3

    new_pop = @population.evolve

    ## Report hook for evaluation
    @report_hook.(@population.report) unless @report_hook.nil?

    ## Exit if fitness criteria is reached
    #FIXME handle this exit condition better!!!!!
    exit if @stop_on_fit_func.(@population.report[:fitness], self) unless @stop_on_fit_func.nil?

    ## Evolve population
    @population = new_pop

    ## Finish up this run
    @end_run_func.(self) unless @end_run_func.nil?
  end
end