# Quick Development/Testing Configuration
#
# Fast configuration for development and testing with short runs.

# Experiment settings
exp_name: "brittle_star_dev_test"
seed: 123

# Tracking settings - IMPORTANT: Set your own wandb_entity!
track: true
wandb_project_name: "PPO-Modularity-Dev"
wandb_entity: "SEL3-2026-Groep-4"  # ⚠️  SET THIS TO YOUR WANDB USERNAME OR TEAM

# Model saving
save_model: true
checkpoint_frequency: 10  # More frequent checkpoints for testing

# Environment settings
num_envs: 4  # Smaller for faster iteration

# Training hyperparameters - Fast/testing
total_timesteps: 100000  # Short run for testing
learning_rate: 0.001  # Higher learning rate for faster learning
num_steps: 64  # Shorter rollouts
anneal_lr: true

# PPO specific - Optimized for quick results
gamma: 0.99
gae_lambda: 0.95
num_minibatches: 2
update_epochs: 2  # Fewer epochs for speed
norm_adv: true
clip_coef: 0.1
clip_vloss: true
ent_coef: 0.02  # Higher entropy for exploration
vf_coef: 0.5
max_grad_norm: 0.5
target_kl: null

# Hardware
cuda: true
torch_deterministic: true