config.yaml

# SPIRAL Interactive Reasoning Game Simulator Configuration

# Model Configuration
model:
  name: "Qwen/Qwen2.5-4B-Instruct"
  max_length: 2048
  temperature: 0.7
  do_sample: true
  quantization:
    load_in_4bit: true
    bnb_4bit_compute_dtype: "float16"
    bnb_4bit_use_double_quant: true

# Games Configuration
games:
  kuhn_poker:
    name: "Kuhn Poker"
    max_rounds: 50
    deck_size: 3
    betting_rounds: 2
    
  tictactoe:
    name: "TicTacToe"
    board_size: 3
    max_moves: 9
    win_condition: 3

# Training Configuration
training:
  algorithm: "PPO"
  episodes: 1000
  batch_size: 32
  learning_rate: 0.0003
  gamma: 0.99
  gae_lambda: 0.95
  clip_range: 0.2
  entropy_coef: 0.01
  value_loss_coef: 0.5
  max_grad_norm: 0.5
  
  # Self-play specific
  self_play:
    update_opponent_every: 100
    opponent_pool_size: 5
    
  # Role-conditioned advantage estimation
  rae:
    enable: true
    role_embedding_dim: 64
    advantage_weighting: 0.5

# Reasoning Configuration
reasoning:
  enable_traces: true
  trace_depth: 3
  chain_of_thought: true
  explanation_length: 150
  
  # Transfer learning evaluation
  transfer_tasks:
    - "GSM8K"
    - "Logic Puzzles"
    - "Strategic Reasoning"

# Web Interface Configuration
interface:
  title: "SPIRAL: Interactive Reasoning Game Simulator"
  description: "Play games against AI and explore reasoning capabilities"
  theme: "default"
  
  # Gradio settings
  gradio:
    share: false
    inbrowser: true
    server_name: "0.0.0.0"
    server_port: 7860
    enable_queue: true
    max_threads: 4

# Logging Configuration
logging:
  level: "INFO"
  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
  file: "logs/spiral.log"
  
  # Experiment tracking
  wandb:
    enable: false
    project: "spiral-reasoning"
    entity: "your-username"
    
  tensorboard:
    enable: true
    log_dir: "logs/tensorboard"

# Data Configuration
data:
  cache_dir: "data/cache"
  datasets_dir: "data/datasets"
  models_dir: "models"
  
  # Benchmark datasets
  benchmarks:
    gsm8k: "data/benchmarks/gsm8k.json"
    logic_puzzles: "data/benchmarks/logic_puzzles.json"

# Deployment Configuration
deployment:
  huggingface:
    space_name: "kaushikvr06/reasoning-simulator"
    private: false
    
  # Performance settings
  performance:
    max_concurrent_users: 10
    timeout_seconds: 30
    memory_limit: "2GB"
    
# Debug Configuration
debug:
  enable: false
  verbose_traces: false
  save_game_logs: true
  profile_inference: false