{
  "initial_table": {
    "A": {
      "L": "2",
      "R": "0"
    },
    "B": {
      "L": "1",
      "R": "4"
    }
  },
  "alpha": "1/4",
  "gamma": "9/10",
  "separate_updates_from_same_initial_table": [
    {
      "old": "2",
      "future": "4",
      "reward": "1",
      "target": "23/5",
      "td_error": "13/5",
      "new": "53/20",
      "terminated": false,
      "truncated": false
    },
    {
      "old": "2",
      "future": "0",
      "reward": "1",
      "target": "1",
      "td_error": "-1",
      "new": "7/4",
      "terminated": true,
      "truncated": false
    },
    {
      "old": "2",
      "future": "4",
      "reward": "1",
      "target": "23/5",
      "td_error": "13/5",
      "new": "53/20",
      "terminated": false,
      "truncated": true
    }
  ],
  "terminal_successor_lookup_skipped": true,
  "environment_executed": false,
  "learned_policy_or_convergence_claimed": false
}
