behaviors:
PushBlock:
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
keep_checkpoints: 5
max_steps: 20000000 #2000000
time_horizon: 64
summary_freq: 60000
threaded: true