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
 
 
 
 
 

191 行
3.4 KiB

default:
trainer: ppo
batch_size: 1024
beta: 5.0e-3
buffer_size: 10240
epsilon: 0.2
gamma: 0.99
hidden_units: 128
lambd: 0.95
learning_rate: 3.0e-4
max_steps: 5.0e4
memory_size: 256
normalize: false
num_epoch: 3
num_layers: 2
time_horizon: 64
sequence_length: 64
summary_freq: 1000
use_recurrent: false
BananaBrain:
normalize: false
batch_size: 1024
beta: 5.0e-3
buffer_size: 10240
PushBlockBrain:
max_steps: 5.0e4
batch_size: 128
buffer_size: 2048
beta: 1.0e-2
hidden_units: 256
summary_freq: 2000
time_horizon: 64
num_layers: 2
SmallWallBrain:
max_steps: 2.0e5
batch_size: 128
buffer_size: 2048
beta: 5.0e-3
hidden_units: 256
summary_freq: 2000
time_horizon: 128
num_layers: 2
normalize: false
BigWallBrain:
max_steps: 2.0e5
batch_size: 128
buffer_size: 2048
beta: 5.0e-3
hidden_units: 256
summary_freq: 2000
time_horizon: 128
num_layers: 2
normalize: false
StrikerBrain:
max_steps: 1.0e5
batch_size: 128
buffer_size: 2048
beta: 5.0e-3
hidden_units: 256
summary_freq: 2000
time_horizon: 128
num_layers: 2
normalize: false
GoalieBrain:
max_steps: 1.0e5
batch_size: 128
buffer_size: 2048
beta: 5.0e-3
hidden_units: 256
summary_freq: 2000
time_horizon: 128
num_layers: 2
normalize: false
Ball3DBrain:
normalize: true
batch_size: 1200
buffer_size: 12000
summary_freq: 1000
time_horizon: 1000
gamma: 0.995
beta: 0.001
Ball3DHardBrain:
normalize: true
batch_size: 1200
buffer_size: 12000
summary_freq: 1000
time_horizon: 1000
gamma: 0.995
beta: 0.001
BouncerBrain:
normalize: true
max_steps: 5.0e5
num_layers: 2
hidden_units: 56
TennisBrain:
normalize: true
CrawlerBrain:
normalize: true
num_epoch: 3
time_horizon: 1000
batch_size: 2024
buffer_size: 20240
gamma: 0.995
max_steps: 1e6
summary_freq: 3000
WalkerBrain:
normalize: true
num_epoch: 3
time_horizon: 1000
batch_size: 2048
buffer_size: 20480
beta: 0.001
gamma: 0.995
max_steps: 2e6
summary_freq: 3000
num_layers: 2
hidden_units: 256
ReacherBrain:
normalize: true
num_epoch: 3
time_horizon: 1000
batch_size: 2024
buffer_size: 20240
gamma: 0.995
max_steps: 1e6
summary_freq: 3000
HallwayBrain:
use_recurrent: true
sequence_length: 64
num_layers: 2
hidden_units: 128
memory_size: 256
beta: 1.0e-2
gamma: 0.99
num_epoch: 3
buffer_size: 1024
batch_size: 128
max_steps: 5.0e5
summary_freq: 1000
time_horizon: 64
GridWorldBrain:
batch_size: 32
normalize: false
num_layers: 1
hidden_units: 256
beta: 5.0e-3
gamma: 0.9
buffer_size: 256
max_steps: 5.0e5
summary_freq: 2000
time_horizon: 5
BasicBrain:
batch_size: 32
normalize: false
num_layers: 1
hidden_units: 20
beta: 5.0e-3
gamma: 0.9
buffer_size: 256
max_steps: 5.0e5
summary_freq: 2000
time_horizon: 3
StudentBrain:
trainer: imitation
max_steps: 10000
summary_freq: 1000
brain_to_imitate: TeacherBrain
batch_size: 16
batches_per_epoch: 5
num_layers: 4
hidden_units: 64
use_recurrent: false
sequence_length: 16
buffer_size: 128