ppo-Pyramids-Training / config /sac /FoodCollector.yaml
AnnaMats's picture
Second Push
05c9ac2
raw
history blame
671 Bytes
behaviors:
GridFoodCollector:
trainer_type: sac
hyperparameters:
learning_rate: 0.0003
learning_rate_schedule: constant
batch_size: 256
buffer_size: 2048
buffer_init_steps: 0
tau: 0.005
steps_per_update: 10.0
save_replay_buffer: false
init_entcoef: 0.05
reward_signal_steps_per_update: 10.0
network_settings:
normalize: false
hidden_units: 256
num_layers: 1
vis_encode_type: simple
reward_signals:
extrinsic:
gamma: 0.99
strength: 1.0
keep_checkpoints: 5
max_steps: 2000000
time_horizon: 64
summary_freq: 60000
threaded: false