ppo-Pyramids-Training / config /ppo /Visual3DBall.yaml
AnnaMats's picture
Second Push
05c9ac2
behaviors:
Visual3DBall:
trainer_type: ppo
hyperparameters:
batch_size: 256
buffer_size: 2560
learning_rate: 0.0003
beta: 0.005
epsilon: 0.2
lambd: 0.95
num_epoch: 3
learning_rate_schedule: linear
network_settings:
normalize: false
hidden_units: 128
num_layers: 2
vis_encode_type: simple
reward_signals:
extrinsic:
gamma: 0.99
strength: 1.0
keep_checkpoints: 5
max_steps: 400000
time_horizon: 64
summary_freq: 20000