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
36 行
762 B
36 行
762 B
behaviors:
|
|
3DBall:
|
|
trainer_type: ppo
|
|
hyperparameters:
|
|
batch_size: 64
|
|
buffer_size: 12000
|
|
learning_rate: 0.0003
|
|
beta: 0.001
|
|
epsilon: 0.2
|
|
lambd: 0.99
|
|
num_epoch: 3
|
|
learning_rate_schedule: linear
|
|
network_settings:
|
|
normalize: true
|
|
hidden_units: 128
|
|
num_layers: 2
|
|
vis_encode_type: simple
|
|
reward_signals:
|
|
extrinsic:
|
|
gamma: 0.99
|
|
strength: 1.0
|
|
keep_checkpoints: 5
|
|
max_steps: 500000
|
|
time_horizon: 1000
|
|
summary_freq: 12000
|
|
environment_parameters:
|
|
mass:
|
|
sampler_type: uniform
|
|
sampler_parameters:
|
|
min_value: 0.5
|
|
max_value: 10
|
|
scale:
|
|
sampler_type: uniform
|
|
sampler_parameters:
|
|
min_value: 0.75
|
|
max_value: 3
|