Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 

54 行
1.3 KiB

behaviors:
CrawlerStatic:
trainer_type: ppo_transfer
hyperparameters:
batch_size: 2024
buffer_size: 20240
learning_rate: 0.0003
beta: 0.005
epsilon: 0.2
lambd: 0.95
num_epoch: 3
learning_rate_schedule: linear
model_schedule: linear
encoder_layers: 2
action_layers: 2
policy_layers: 2
forward_layers: 0
value_layers: 2
feature_size: 128
action_feature_size: 128
reuse_encoder: false
in_epoch_alter: false
use_op_buffer: false
use_var_predict: true
with_prior: false
predict_return: true
use_bisim: false
separate_value_train: true
train_model: false
load_model: true
train_action: false
load_action: true
train_policy: true
load_policy: false
train_value: true
load_value: false
transfer_path: "results/cs-tr-s1/CrawlerStatic"
use_transfer: true
in_batch_alter: true
network_settings:
normalize: true
hidden_units: 512
num_layers: 3
vis_encode_type: simple
reward_signals:
extrinsic:
gamma: 0.995
strength: 1.0
keep_checkpoints: 5
max_steps: 10000000
time_horizon: 1000
summary_freq: 30000
threaded: true
transfer: true