- Try to increase the value of the node_add_prob parameter and see what happens. Does the algorithm produce any number of hidden nodes, and if so, how many?
- Try to decrease/increase the compatibility_threshold value. What happens if you set it to 2.0 or 6.0? Can the algorithm find the solution in each case?
- Try to set the elitism value to zero in the DefaultReproduction section. See what happens. How long did the evolutionary process take to find an acceptable solution in this case?
- Set the survival_threshold value to 0.5 in the DefaultReproduction section. See how this affects speciation during evolution. Why does it?
- Increase the additional_num_runs and additional_steps values in order of magnitude to examine further how well the found control strategy is generalized. Is the algorithm still able to find a winning solution?
You're reading from Hands-On Neuroevolution with Python.
The last exercise will lead to an increase...
The rest of the page is locked
You have been reading a chapter from
Hands-On Neuroevolution with Python.Published in: Dec 2019Publisher: PacktISBN-13: 9781838824914
© 2019 Packt Publishing Limited All Rights Reserved