reports/simulation_report.json

{
  "total_episodes": 30,
  "wpr_mean_reward": 8.4,
  "baseline_mean_reward": 5.1,
  "wpr_episodes": [
    {"episode_id": 0, "reward": 8.4, "steps": 12, "productive_steps": 10},
    {"episode_id": 1, "reward": 8.9, "steps": 12, "productive_steps": 11},
    {"episode_id": 2, "reward": 7.8, "steps": 12, "productive_steps": 9},
    {"episode_id": 3, "reward": 8.6, "steps": 12, "productive_steps": 10},
    {"episode_id": 4, "reward": 8.2, "steps": 12, "productive_steps": 10}
  ],
  "baseline_episodes": [
    {"episode_id": 0, "reward": 5.1, "steps": 12, "productive_steps": 6},
    {"episode_id": 1, "reward": 5.8, "steps": 12, "productive_steps": 7},
    {"episode_id": 2, "reward": 4.5, "steps": 12, "productive_steps": 5},
    {"episode_id": 3, "reward": 5.3, "steps": 12, "productive_steps": 6},
    {"episode_id": 4, "reward": 4.9, "steps": 12, "productive_steps": 5}
  ]
}