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
37 行
825 B
37 行
825 B
behaviors:
|
|
DodgeBall:
|
|
trainer_type: ppo
|
|
hyperparameters:
|
|
batch_size: 1024
|
|
buffer_size: 10240
|
|
learning_rate: 0.0003
|
|
beta: 0.01
|
|
epsilon: 0.2
|
|
lambd: 0.95
|
|
num_epoch: 3
|
|
learning_rate_schedule: constant
|
|
network_settings:
|
|
normalize: false
|
|
hidden_units: 256
|
|
num_layers: 2
|
|
vis_encode_type: simple
|
|
reward_signals:
|
|
extrinsic:
|
|
gamma: 0.99
|
|
strength: 1.0
|
|
# reward_signals:
|
|
# extrinsic:
|
|
# gamma: 0.99
|
|
# strength: 1.0
|
|
# curiosity:
|
|
# gamma: 0.99
|
|
# strength: 0.02
|
|
# encoding_size: 256
|
|
# learning_rate: 0.0003
|
|
keep_checkpoints: 5
|
|
max_steps: 50000000
|
|
time_horizon: 64
|
|
summary_freq: 20000
|
|
threaded: true
|
|
env_settings:
|
|
num_envs: 8
|