Suggestion: Config

[jsykes]

I was never able to get past fitness 60-80 with the config file in the repo. I grabbed the one from the neat-python repo for openai lander and was able to hit a fitness of 300 max score for regular level on generation 309.

NEAT configuration for the bit-sequence memory experiment.

The NEAT section specifies parameters particular to the NEAT algorithm

or the experiment itself. This is the only required section.

[NEAT] fitness_criterion = max fitness_threshold = 300 pop_size = 250 reset_on_extinction = 0

[DefaultGenome] num_inputs = 24 num_hidden = 0 num_outputs = 4 initial_connection = partial 0.5 feed_forward = True compatibility_disjoint_coefficient = 1.0 compatibility_weight_coefficient = 1.0 conn_add_prob = 0.15 conn_delete_prob = 0.1 node_add_prob = 0.15 node_delete_prob = 0.1 activation_default = clamped activation_options = clamped activation_mutate_rate = 0.0 aggregation_default = sum aggregation_options = sum aggregation_mutate_rate = 0.0 bias_init_mean = 0.0 bias_init_stdev = 1.0 bias_replace_rate = 0.02 bias_mutate_rate = 0.8 bias_mutate_power = 0.4 bias_max_value = 30.0 bias_min_value = -30.0 response_init_mean = 1.0 response_init_stdev = 0.0 response_replace_rate = 0.0 response_mutate_rate = 0.1 response_mutate_power = 0.01 response_max_value = 30.0 response_min_value = -30.0

weight_max_value = 30 weight_min_value = -30 weight_init_mean = 0.0 weight_init_stdev = 1.0 weight_mutate_rate = 0.8 weight_replace_rate = 0.02 weight_mutate_power = 0.4 enabled_default = True enabled_mutate_rate = 0.01

[DefaultSpeciesSet] compatibility_threshold = 3.0

[DefaultStagnation] species_fitness_func = max max_stagnation = 15 species_elitism = 4

[DefaultReproduction] elitism = 2 survival_threshold = 0.2