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
 
 
 
 
 

44 行
1.1 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
encoder_layers: 2
policy_layers: 2
forward_layers: 2
value_layers: 3
feature_size: 128
reuse_encoder: true
in_epoch_alter: true
use_op_buffer: true
use_var_predict: true
with_prior: true
predict_return: true
# use_bisim: true
separate_value_net: true
use_transfer: true
load_policy: false
load_value: false
train_model: false
transfer_path: "results/new_crawler_single_2-2-3o-2_rew_varp_f128/CrawlerStatic"
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