# PPO Training Configuration Template
#
# This file provides an example configuration for PPO training.
# Copy this file and modify it for your specific experiments.
#
# Usage:
#   python src/train.py --config-path configs/my_config.yaml
# Or override specific parameters:
#   python src/train.py --learning-rate 0.001 --num-envs 32

# Experiment settings
exp_name: "brittle_star_ppo"
seed: 1

# Tracking settings
track: false  # Set to true to enable WandB logging
wandb_project_name: "PPO-Modularity"
wandb_entity: "SEL3-2026-Groep-4"  # Set to your WandB username or team name

# Model saving
save_model: true
checkpoint_frequency: 100  # Save checkpoint every N iterations (0 = no checkpoints)

# Environment settings
num_envs: 16

# Training hyperparameters
total_timesteps: 10000000
learning_rate: 0.00025
num_steps: 128
anneal_lr: true

# PPO specific
gamma: 0.99
gae_lambda: 0.95
num_minibatches: 4
update_epochs: 4
norm_adv: true
clip_coef: 0.1
clip_vloss: true
ent_coef: 0.01
vf_coef: 0.5
max_grad_norm: 0.5
target_kl: null

# Hardware
cuda: true
torch_deterministic: true