# Full PPO training config for Brittle Star (HPC Production)
exp_name: "production_training"
seed: 1
track: true
capture_video: true
save_model: true
checkpoint_frequency: 100  # not yet implemented in train.py but here for future use

# Scaling for HPC (using A100 GPU slices)
num_envs: 128
total_timesteps: 10000000
num_steps: 128
num_minibatches: 4
update_epochs: 4

# Algorithm
learning_rate: 2.5e-4
anneal_lr: true
gamma: 0.99
gae_lambda: 0.95
clip_coef: 0.1
ent_coef: 0.01
vf_coef: 0.5
cuda: true