python - 如何修复Python Neat Openai Retro中的配置错误

标签 python error-handling config openai-gym neat

遵循以下指南:https://www.youtube.com/watch?v=8dY3nQRcsac&list=PLTWFMbPFsvz3CeozHfeuJIXWAJMkPtAdS&index=7

当我运行python程序时,python整洁的配置文件中有错误

看起来与基因组变量有关

我的python整洁的配置文件

#--- parameters for the XOR-2 experiment ---#

[NEAT]
fitness_criterion     = max
fitness_threshold     = 10000
pop_size              = 20
reset_on_extinction   = True

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

# node aggregation options
aggregation_default     = sum
aggregation_mutate_rate = 0.05
aggregation_options     = sum

# node bias options
bias_init_mean          = 0.0
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        = 0.5

# connection enable options
enabled_default         = True
enabled_mutate_rate     = 0.01

feed_forward            = False
initial_connection      = unconn nected

# node add/remove rates
node_add_prob           = 0.5
node_delete_prob        = 0.2

# network parameters
num_hidden              = 0
num_inputs              = 1120
num_outputs             = 12

# node response options
response_init_mean      = 1.0
response_init_stdev     = 0.0
response_max_value      = 30.0
response_min_value      = -30.0
response_mutate_power   = 0.0
response_mutate_rate    = 0.0
response_replace_rate   = 0.0

# connection weight options
weight_init_mean        = 0.0
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 = 205

[DefaultStagnation]
species_fitness_func = max
max_stagnation       = 50
species_elitism      = 0

[DefaultReproduction]
elitism            = 3
survival_threshold = 0.2

来自终端的错误代码
    'config-feedforward')
  File "/home/gym/OPAI/lib/python3.6/site-packages/neat/config.py", line 189, in __init__
    self.genome_config = genome_type.parse_config(genome_dict)
  File "/home/gym/OPAI/lib/python3.6/site-packages/neat/genome.py", line 158, in parse_config
    return DefaultGenomeConfig(param_dict)
  File "/home/gym/OPAI/lib/python3.6/site-packages/neat/genome.py", line 72, in __init__
    assert self.initial_connection in self.allowed_connectivity
AssertionError

来自python整洁代码的配置代码
config = neat.Config(neat.DefaultGenome, neat.DefaultReproduction,
                     neat.DefaultSpeciesSet, neat.DefaultStagnation,
                     config-feedforward')

最佳答案

问题是在读取“initial_connection =未连接”的行上

有错别字。 “未连接”不应中断。其内容如下:
“初始连接=未连接”

关于python - 如何修复Python Neat Openai Retro中的配置错误,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/55313995/

相关文章:

grails - 在共享同一个插件的两个grails应用之间共享配置

javascript - Webpack 编号的 block 未根据配置正确加载

java - 每次程序执行如何在 log4j 中创建日志文件?

linq-to-sql - SQL 不会在 INSERT 错误时增加主键

python - readAll() 或 readAllStandardOutput() 在执行之前返回一个空字符串

Python 扩展了一个空列表错误?

python - 从 2D numpy 数组的 numpy 数组高效创建 block numpy 数组

c - 如何使用条件#error

javascript - Bluebird .js : Re-Throwing the error in catch callback is not caught again

python - 使用 Python Eve 添加 mongoDB 文档数组元素