{
  "authored_initial_Q_unchanged": {
    "Start": {
      "wait": "3",
      "send": "1"
    },
    "Fork": {
      "steady": "2",
      "risky": "8"
    }
  },
  "behavior_action_contract": "two manually declared alternatives, each passed into the update; no random behavior policy or real environment sampled",
  "same_snapshot_four_continuing_updates": [
    {
      "rule": "qlearning",
      "state": "Start",
      "action": "wait",
      "reward": "-2",
      "next_state": "Fork",
      "declared_behavior_next_action": "steady",
      "terminal": false,
      "source_next_Q_row": {
        "steady": "2",
        "risky": "8"
      },
      "bootstrap_action_used_by_rule": "risky",
      "bootstrap_Q_value": "8",
      "old": "3",
      "target": "2",
      "TD_error": "-1",
      "alpha": "1/5",
      "gamma": "1/2",
      "new": "14/5",
      "Q_after": {
        "Start": {
          "wait": "14/5",
          "send": "1"
        },
        "Fork": {
          "steady": "2",
          "risky": "8"
        }
      },
      "all_nonupdated_cells_unchanged": true
    },
    {
      "rule": "sarsa",
      "state": "Start",
      "action": "wait",
      "reward": "-2",
      "next_state": "Fork",
      "declared_behavior_next_action": "steady",
      "terminal": false,
      "source_next_Q_row": {
        "steady": "2",
        "risky": "8"
      },
      "bootstrap_action_used_by_rule": "steady",
      "bootstrap_Q_value": "2",
      "old": "3",
      "target": "-1",
      "TD_error": "-4",
      "alpha": "1/5",
      "gamma": "1/2",
      "new": "11/5",
      "Q_after": {
        "Start": {
          "wait": "11/5",
          "send": "1"
        },
        "Fork": {
          "steady": "2",
          "risky": "8"
        }
      },
      "all_nonupdated_cells_unchanged": true
    },
    {
      "rule": "qlearning",
      "state": "Start",
      "action": "wait",
      "reward": "-2",
      "next_state": "Fork",
      "declared_behavior_next_action": "risky",
      "terminal": false,
      "source_next_Q_row": {
        "steady": "2",
        "risky": "8"
      },
      "bootstrap_action_used_by_rule": "risky",
      "bootstrap_Q_value": "8",
      "old": "3",
      "target": "2",
      "TD_error": "-1",
      "alpha": "1/5",
      "gamma": "1/2",
      "new": "14/5",
      "Q_after": {
        "Start": {
          "wait": "14/5",
          "send": "1"
        },
        "Fork": {
          "steady": "2",
          "risky": "8"
        }
      },
      "all_nonupdated_cells_unchanged": true
    },
    {
      "rule": "sarsa",
      "state": "Start",
      "action": "wait",
      "reward": "-2",
      "next_state": "Fork",
      "declared_behavior_next_action": "risky",
      "terminal": false,
      "source_next_Q_row": {
        "steady": "2",
        "risky": "8"
      },
      "bootstrap_action_used_by_rule": "risky",
      "bootstrap_Q_value": "8",
      "old": "3",
      "target": "2",
      "TD_error": "-1",
      "alpha": "1/5",
      "gamma": "1/2",
      "new": "14/5",
      "Q_after": {
        "Start": {
          "wait": "14/5",
          "send": "1"
        },
        "Fork": {
          "steady": "2",
          "risky": "8"
        }
      },
      "all_nonupdated_cells_unchanged": true
    }
  ],
  "two_terminal_no_next_row_updates": [
    {
      "rule": "qlearning",
      "state": "Start",
      "action": "wait",
      "reward": "-2",
      "next_state": null,
      "declared_behavior_next_action": null,
      "terminal": true,
      "source_next_Q_row": null,
      "bootstrap_action_used_by_rule": null,
      "bootstrap_Q_value": "0",
      "old": "3",
      "target": "-2",
      "TD_error": "-5",
      "alpha": "1/5",
      "gamma": "1/2",
      "new": "2",
      "Q_after": {
        "Start": {
          "wait": "2",
          "send": "1"
        },
        "Fork": {
          "steady": "2",
          "risky": "8"
        }
      },
      "all_nonupdated_cells_unchanged": true
    },
    {
      "rule": "sarsa",
      "state": "Start",
      "action": "wait",
      "reward": "-2",
      "next_state": null,
      "declared_behavior_next_action": null,
      "terminal": true,
      "source_next_Q_row": null,
      "bootstrap_action_used_by_rule": null,
      "bootstrap_Q_value": "0",
      "old": "3",
      "target": "-2",
      "TD_error": "-5",
      "alpha": "1/5",
      "gamma": "1/2",
      "new": "2",
      "Q_after": {
        "Start": {
          "wait": "2",
          "send": "1"
        },
        "Fork": {
          "steady": "2",
          "risky": "8"
        }
      },
      "all_nonupdated_cells_unchanged": true
    }
  ],
  "missing_SARSA_next_action_rejected": true,
  "multi_episode_training_convergence_or_Gymnasium_executed": false
}