{
  "config": {
    "levers": 10,
    "best_payoff": 1.0,
    "other_payoff": 0.9,
    "seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ],
    "steps": 10000,
    "batch": 512,
    "learning_rate": 0.2,
    "init_logit_scale": 0.5
  },
  "barrier": 0.090909,
  "environment": {
    "python": "3.14.6",
    "numpy": "2.4.4",
    "platform": "macOS-26.6.2-arm64-arm-64bit-Mach-O"
  },
  "regimes": {
    "self_play": {
      "matrix": [
        [
          0.8995,
          0.0,
          0.0,
          0.0,
          0.0001,
          0.0,
          0.0001,
          0.0001
        ],
        [
          0.0,
          0.8995,
          0.8995,
          0.0001,
          0.0,
          0.0001,
          0.0001,
          0.0001
        ],
        [
          0.0,
          0.8995,
          0.8995,
          0.0,
          0.0,
          0.0001,
          0.0001,
          0.0001
        ],
        [
          0.0,
          0.0001,
          0.0,
          0.8995,
          0.0001,
          0.8995,
          0.0,
          0.0001
        ],
        [
          0.0001,
          0.0,
          0.0,
          0.0001,
          0.8996,
          0.0001,
          0.0,
          0.0001
        ],
        [
          0.0,
          0.0001,
          0.0001,
          0.8995,
          0.0001,
          0.8995,
          0.0,
          0.0
        ],
        [
          0.0001,
          0.0001,
          0.0001,
          0.0,
          0.0,
          0.0,
          0.8995,
          0.0001
        ],
        [
          0.0001,
          0.0001,
          0.0001,
          0.0001,
          0.0001,
          0.0,
          0.0001,
          0.8995
        ]
      ],
      "lever_chosen": [
        6,
        4,
        4,
        9,
        2,
        9,
        1,
        7
      ],
      "mass_on_chosen_lever": [
        0.9997,
        0.9997,
        0.9997,
        0.9997,
        0.9998,
        0.9997,
        0.9997,
        0.9997
      ],
      "q_init": [
        0.0955,
        0.1018,
        0.0961,
        0.1995,
        0.0711,
        0.0594,
        0.1134,
        0.1044
      ],
      "q_final": [
        0.0,
        0.0,
        0.0,
        0.0,
        0.0,
        0.0,
        0.0,
        0.0
      ],
      "started_above_barrier": [
        true,
        true,
        true,
        true,
        false,
        false,
        true,
        true
      ],
      "distinct_levers": 6,
      "seeds_on_the_best_lever": 0,
      "self_play_mean": 0.8995,
      "self_play_min": 0.8995,
      "cross_play_mean": 0.0643,
      "cross_play_min": 0.0,
      "cross_play_max": 0.8995,
      "self_play_over_cross_play": 13.99,
      "q_final_above_barrier": [
        0.0
      ],
      "q_final_below_barrier": [
        0.0
      ]
    },
    "other_play": {
      "matrix": [
        [
          0.9995,
          0.9995,
          0.9995,
          0.9995,
          0.0025,
          0.0024,
          0.9995,
          0.9995
        ],
        [
          0.9995,
          0.9995,
          0.9995,
          0.9995,
          0.0025,
          0.0024,
          0.9995,
          0.9995
        ],
        [
          0.9995,
          0.9995,
          0.9995,
          0.9995,
          0.0025,
          0.0024,
          0.9995,
          0.9995
        ],
        [
          0.9995,
          0.9995,
          0.9995,
          0.9995,
          0.0025,
          0.0024,
          0.9995,
          0.9995
        ],
        [
          0.0025,
          0.0025,
          0.0025,
          0.0025,
          0.1536,
          0.089,
          0.0025,
          0.0025
        ],
        [
          0.0024,
          0.0024,
          0.0024,
          0.0024,
          0.089,
          0.1389,
          0.0024,
          0.0024
        ],
        [
          0.9995,
          0.9995,
          0.9995,
          0.9995,
          0.0025,
          0.0024,
          0.9995,
          0.9995
        ],
        [
          0.9995,
          0.9995,
          0.9995,
          0.9995,
          0.0025,
          0.0024,
          0.9995,
          0.9995
        ]
      ],
      "lever_chosen": [
        0,
        0,
        0,
        0,
        2,
        9,
        0,
        0
      ],
      "mass_on_chosen_lever": [
        0.9998,
        0.9998,
        0.9998,
        0.9998,
        0.3145,
        0.2627,
        0.9998,
        0.9998
      ],
      "q_init": [
        0.0955,
        0.1018,
        0.0961,
        0.1995,
        0.0711,
        0.0594,
        0.1134,
        0.1044
      ],
      "q_final": [
        0.9998,
        0.9998,
        0.9998,
        0.9998,
        0.0024,
        0.0024,
        0.9998,
        0.9998
      ],
      "started_above_barrier": [
        true,
        true,
        true,
        true,
        false,
        false,
        true,
        true
      ],
      "distinct_levers": 3,
      "seeds_on_the_best_lever": 6,
      "self_play_mean": 0.7862,
      "self_play_min": 0.1389,
      "cross_play_mean": 0.5397,
      "cross_play_min": 0.0024,
      "cross_play_max": 0.9995,
      "self_play_over_cross_play": 1.46,
      "q_final_above_barrier": [
        0.9998
      ],
      "q_final_below_barrier": [
        0.0024
      ]
    }
  }
}
