{
  "authored_known_MDP": {
    "A": {
      "quit": [
        [
          "1",
          "T",
          "1"
        ]
      ],
      "try": [
        [
          "1/2",
          "B",
          "0"
        ],
        [
          "1/2",
          "T",
          "4"
        ]
      ]
    },
    "B": {
      "finish": [
        [
          "1",
          "T",
          "3"
        ]
      ],
      "wait": [
        [
          "1",
          "B",
          "1"
        ]
      ]
    },
    "T": {}
  },
  "reward_convention": "per transition, includes terminal-entry reward exactly once; terminal has no actions and V0",
  "gamma": "1/2",
  "two_synchronous_sweeps": {
    "sweeps": 2,
    "trace": [
      {
        "sweep": 1,
        "V_before": {
          "A": "0",
          "B": "0",
          "T": "0"
        },
        "Q_from_previous_snapshot": {
          "A": {
            "quit": "1",
            "try": "2"
          },
          "B": {
            "finish": "3",
            "wait": "1"
          },
          "T": {}
        },
        "V_after": {
          "A": "2",
          "B": "3",
          "T": "0"
        }
      },
      {
        "sweep": 2,
        "V_before": {
          "A": "2",
          "B": "3",
          "T": "0"
        },
        "Q_from_previous_snapshot": {
          "A": {
            "quit": "1",
            "try": "11/4"
          },
          "B": {
            "finish": "3",
            "wait": "5/2"
          },
          "T": {}
        },
        "V_after": {
          "A": "11/4",
          "B": "3",
          "T": "0"
        }
      }
    ],
    "reported_V": {
      "A": "11/4",
      "B": "3",
      "T": "0"
    },
    "fresh_Bellman_backup": {
      "A": "11/4",
      "B": "3",
      "T": "0"
    },
    "Bellman_residual_infinity": "0",
    "greedy_policy_from_reported_V": {
      "A": "try",
      "B": "finish",
      "T": null
    },
    "exact_fixed_point_in_this_run": true
  },
  "one_sweep_not_fixed": {
    "sweeps": 1,
    "trace": [
      {
        "sweep": 1,
        "V_before": {
          "A": "0",
          "B": "0",
          "T": "0"
        },
        "Q_from_previous_snapshot": {
          "A": {
            "quit": "1",
            "try": "2"
          },
          "B": {
            "finish": "3",
            "wait": "1"
          },
          "T": {}
        },
        "V_after": {
          "A": "2",
          "B": "3",
          "T": "0"
        }
      }
    ],
    "reported_V": {
      "A": "2",
      "B": "3",
      "T": "0"
    },
    "fresh_Bellman_backup": {
      "A": "11/4",
      "B": "3",
      "T": "0"
    },
    "Bellman_residual_infinity": "3/4",
    "greedy_policy_from_reported_V": {
      "A": "try",
      "B": "finish",
      "T": null
    },
    "exact_fixed_point_in_this_run": false
  },
  "four_stationary_deterministic_policy_oracle": [
    {
      "policy": {
        "A": "quit",
        "B": "finish",
        "T": null
      },
      "independently_solved_V": {
        "A": "1",
        "B": "3",
        "T": "0"
      }
    },
    {
      "policy": {
        "A": "quit",
        "B": "wait",
        "T": null
      },
      "independently_solved_V": {
        "A": "1",
        "B": "2",
        "T": "0"
      }
    },
    {
      "policy": {
        "A": "try",
        "B": "finish",
        "T": null
      },
      "independently_solved_V": {
        "A": "11/4",
        "B": "3",
        "T": "0"
      }
    },
    {
      "policy": {
        "A": "try",
        "B": "wait",
        "T": null
      },
      "independently_solved_V": {
        "A": "5/2",
        "B": "2",
        "T": "0"
      }
    }
  ],
  "experience_learning_or_Gymnasium_executed": false
}