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
29 行
687 B
29 行
687 B
behaviors:
|
|
GridWorld:
|
|
trainer_type: sac
|
|
hyperparameters:
|
|
learning_rate: 0.0003
|
|
learning_rate_schedule: constant
|
|
batch_size: 128
|
|
buffer_size: 50000
|
|
buffer_init_steps: 1000
|
|
tau: 0.005
|
|
steps_per_update: 10.0
|
|
save_replay_buffer: false
|
|
init_entcoef: 0.5
|
|
reward_signal_steps_per_update: 10.0
|
|
network_settings:
|
|
normalize: false
|
|
hidden_units: 128
|
|
num_layers: 1
|
|
vis_encode_type: simple
|
|
reward_signals:
|
|
extrinsic:
|
|
gamma: 0.9
|
|
strength: 1.0
|
|
output_path: default
|
|
keep_checkpoints: 5
|
|
max_steps: 500000
|
|
time_horizon: 5
|
|
summary_freq: 20000
|
|
threaded: true
|