Repository files navigation

This is a library of evolutionary algorithms with a focus on neuroevolution, implemented in pure python, depending on theneat-python implementation. It contains a faithful implementation of both HyperNEAT and ES-HyperNEAT which are briefly described below.

NEAT (NeuroEvolution of Augmenting Topologies) is a method developed by Kenneth O. Stanley for evolving arbitrary neural networks.
HyperNEAT (Hypercube-based NEAT) is a method developed by Kenneth O. Stanley utilizing NEAT. It is a technique for evolving large-scale neural networks using the geometric regularities of the task domain.
ES-HyperNEAT (Evolvable-substrate HyperNEAT) is a method developed by Sebastian Risi and Kenneth O. Stanley utilizing HyperNEAT. It is a technique for evolving large-scale neural networks using the geometric regularities of the task domain. In contrast to HyperNEAT, the substrate used during evolution is able to evolve. This rids the user of some initial work and often creates a more suitable substrate.

The library is extensible in regards to easy transition between experimental domains.

This section briefly describes how to install and run experiments.

First, make sure you have the dependencies installed:numpy,neat-python,graphviz,matplotlib andgym.
All the above can be installed usingpip.
Next, download the source code and runsetup.py (pip install .) from the root folder. Now you're able to usePUREPLES!

How to experiment using NEAT will not be described, since this is the responsibility of theneat-python library.

Setting up an experiment forHyperNEAT:

• Define a substrate with input nodes and output nodes as a list of tuples. The hidden nodes is a list of lists of tuples where the inner lists represent layers. The first list is the topmost layer, the last the bottommost.
• Create a configuration file defining various NEAT specific parameters which are used for the CPPN.
• Define a fitness function setting the fitness of each genome. This is where the CPPN and the ANN is constructed for each generation - use thecreate_phenotype_network method from thehyperneat module.
• Create a population with the configuration file made in (2).
• Run the population with the fitness function made in (3) and the configuration file made in (2). The output is the genome solving the task or the one closest to solving it.

Setting up an experiment forES-HyperNEAT:Use the same setup as HyperNEAT except for:

• Not declaring hidden nodes when defining the substrate.
• Declaring ES-HyperNEAT specific parameters.
• Using thecreate_phenotype_network method residing in thees_hyperneat module when creating the ANN.

If one is trying to solve an experiment defined by theOpenAI Gym it is even easier to experiment. In theshared module a file calledgym_runner is able to do most of the work. Given the number of generations, the environment to run, a configuration file, and a substrate, the relevant runner will take care of everything regarding population, fitness function etc.

Please refer to the sample experiments included for further details on experimenting.