{
  "data": {
    "tickers": [
      "AAPL",
      "MSFT",
      "GOOGL",
      "AMZN",
      "TSLA"
    ],
    "period": "5y",
    "interval": "1d",
    "use_sp500": false
  },
  "environment": {
    "initial_balance": 10000,
    "transaction_cost": 0.001,
    "max_position_size": 1.0,
    "lookback_window": 60,
    "reward_type": "return"
  },
  "training": {
    "algorithm": "PPO",
    "total_timesteps": 500000,
    "learning_rate": 0.0003,
    "batch_size": 64,
    "n_epochs": 10,
    "gamma": 0.99,
    "eval_freq": 1000,
    "n_eval_episodes": 5,
    "save_freq": 10000,
    "seed": 42
  }
}