Files
racesm/MLAgents/config/ppo/FoodCollector.yaml
2024-04-20 14:45:47 +02:00

26 lines
552 B
YAML

behaviors:
GridFoodCollector:
trainer_type: ppo
hyperparameters:
batch_size: 1024
buffer_size: 10240
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: 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: 10000