# Word Hunt Environment Example Configuration
# Copy this file and modify as needed for your training runs

# Environment Configuration
env_name: "word_hunt_environment"
env_config:
  # Core Training Parameters
  group_size: 4
  max_token_length: 2048
  steps_per_eval: 100
  boards_per_epoch: 50

  # Game Parameters
  board_size: 4
  min_word_length: 3
  max_word_length: 16
  max_tokens_per_game: 100

  # Board Generation
  vowel_weight: 0.4
  common_letter_bias: true
  board_generation_method: "random_weighted"

  # Scoring
  use_official_scoring: true
  normalize_scores: true
  max_possible_score_estimate: 10000

  # Validation
  validate_words: true
  validate_board_paths: true

  # Prompt Configuration
  prompt_style: "grid_visual"  # Options: grid_visual, text_description, both
  include_instructions: true
  include_scoring_info: true

  # Evaluation
  eval_board_count: 10
  eval_metrics: ["accuracy", "total_score", "word_count", "avg_word_length"]

  # Logging
  debug_mode: false
  use_wandb: true
  wandb_name: "word_hunt_training"

  # Advanced Options
  shuffle_boards: true
  save_board_images: false

# Server Configuration (example)
server_configs:
  - name: "openai"
    server_type: "openai"
    api_key: "${OPENAI_API_KEY}"
    base_url: "https://api.openai.com/v1"
    model: "gpt-4"
    max_retries: 3
    timeout: 60

# Training Parameters
training:
  total_steps: 10000
  batch_size: 512
  learning_rate: 1e-5
  warmup_steps: 100
  gradient_accumulation_steps: 1

# Logging Configuration
logging:
  log_level: "INFO"
  save_checkpoints: true
  checkpoint_interval: 1000
  save_rollouts: false
  rollout_save_interval: 500