25 lines
547 B
YAML
25 lines
547 B
YAML
behaviors:
|
|
RollerBall:
|
|
trainer_type: ppo
|
|
hyperparameters:
|
|
batch_size: 10
|
|
buffer_size: 100
|
|
learning_rate: 3.0e-4
|
|
beta: 5.0e-4
|
|
epsilon: 0.2
|
|
lambd: 0.99
|
|
num_epoch: 3
|
|
learning_rate_schedule: linear
|
|
beta_schedule: constant
|
|
epsilon_schedule: linear
|
|
network_settings:
|
|
normalize: false
|
|
hidden_units: 128
|
|
num_layers: 2
|
|
reward_signals:
|
|
extrinsic:
|
|
gamma: 0.99
|
|
strength: 1.0
|
|
max_steps: 500000
|
|
time_horizon: 64
|
|
summary_freq: 10000 |