default:
trainer: ppo
batch_size: 1024
beta: 5.0e-3
buffer_size: 10240
epsilon: 0.2
hidden_units: 128
lambd: 0.95
learning_rate: 3.0e-4
learning_rate_schedule: linear
max_steps: 5.0e5
memory_size: 128
normalize: false
num_epoch: 3
num_layers: 2
time_horizon: 64
sequence_length: 64
summary_freq: 10000
use_recurrent: false
vis_encode_type: simple
reward_signals:
extrinsic:
strength: 1.0
gamma: 0.99
Bouncer:
normalize: true
max_steps: 125000
hidden_units: 64
max_steps: 1.0e6