如何配置NEATpython configfeedforward?

2024-05-14 19:48:33 发布

您现在位置:Python中文网/ 问答频道 /正文

我正在用NEAT-python做一个SuperMario-Gamebot。我完成了所有的事情,让进化开始运行。但是我的球员在关卡上不能再移动一点。我什么都试过了。我的意思是我已经尝试了config-feedforward文件的6种参数组合。并连续运行每个测试用例超过2-3天。还是不行。健康水平不断下降。以下是我最近5个版本的健身水平图。 enter image description hereenter image description hereenter image description hereenter image description hereThis is the latest version I'm currently running.

我现在运行的是4.0.3版本,它也一直在下降。以下是版本的配置前馈文件。你知道吗

[NEAT]
fitness_criterion     = max
fitness_threshold     = 1000000
pop_size              = 11
reset_on_extinction   = True

[DefaultGenome]
# node activation options
activation_default      = sigmoid
activation_mutate_rate  = 0.05
activation_options      = sigmoid gauss

# node aggregation options
aggregation_default     = random
aggregation_mutate_rate = 0.05
aggregation_options     = sum product min max mean median maxabs

# node bias options
bias_init_mean          = 0.05
bias_init_stdev         = 1.0
bias_max_value          = 30.0
bias_min_value          = -30.0
bias_mutate_power       = 0.5
bias_mutate_rate        = 0.7
bias_replace_rate       = 0.1

# genome compatibility options
compatibility_disjoint_coefficient = 1.0
compatibility_weight_coefficient   = 0.5

# connection add/remove rates
conn_add_prob           = 0.5
conn_delete_prob        = 0.1

# connection enable options
enabled_default         = True
enabled_mutate_rate     = 0.2

feed_forward            = False
initial_connection      = partial_nodirect 0.5

# node add/remove rates
node_add_prob           = 0.5
node_delete_prob        = 0.5

# network parameters
num_hidden              = 0
num_inputs              = 840
num_outputs             = 9

# node response options
response_init_mean      = 1.0
response_init_stdev     = 0.05
response_max_value      = 30.0
response_min_value      = -30.0
response_mutate_power   = 0.1
response_mutate_rate    = 0.75
response_replace_rate   = 0.1

# connection weight options
weight_init_mean        = 0.1
weight_init_stdev       = 1.0
weight_max_value        = 30
weight_min_value        = -30
weight_mutate_power     = 0.5
weight_mutate_rate      = 0.8
weight_replace_rate     = 0.1

[DefaultSpeciesSet]
compatibility_threshold = 2.5

[DefaultStagnation]
species_fitness_func = max
max_stagnation       = 20
species_elitism      = 1

[DefaultReproduction]
elitism            = 3
survival_threshold = 0.3

有人,请告诉我怎么继续。为了达到更高的健康水平,我应该做些什么改变?你知道吗


Tags: noderateinitvalueresponseminmeanactivation

热门问题