Running the double-pole balancing experiment

Having implemented the two-pole balancing simulator, genome fitness function evaluator, and experiment runner code, we are ready to start experimenting. Enter the directory containing the file and execute the following command:

$ python
Do not forget to activate the appropriate virtual environment with the following command: conda activate double_pole_neat

The preceding command will launch the evolutionary process under the control of the NEAT algorithm, using the hyperparameters specified in the two_pole_markov_config.ini file, as well as the simulator of the cart-two-pole apparatus that we already implemented.

After 96 generations, the ...

Get Hands-On Neuroevolution with Python now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.