{
  "states": [
    0,
    1,
    2,
    3
  ],
  "initial_state": 0,
  "goal_state": 3,
  "actions": [
    "L",
    "R"
  ],
  "step_limit": 4,
  "reward": "5 on reaching goal, -1 otherwise",
  "gamma": "9/10",
  "traces": {
    "goal": {
      "trace": [
        {
          "state": 0,
          "action": "R",
          "next_state": 1,
          "reward": -1,
          "terminated": false,
          "truncated": false
        },
        {
          "state": 1,
          "action": "R",
          "next_state": 2,
          "reward": -1,
          "terminated": false,
          "truncated": false
        },
        {
          "state": 2,
          "action": "R",
          "next_state": 3,
          "reward": 5,
          "terminated": true,
          "truncated": false
        }
      ],
      "reward_sum": 3,
      "gamma": "9/10",
      "discounted_return": "43/20"
    },
    "limit": {
      "trace": [
        {
          "state": 0,
          "action": "R",
          "next_state": 1,
          "reward": -1,
          "terminated": false,
          "truncated": false
        },
        {
          "state": 1,
          "action": "L",
          "next_state": 0,
          "reward": -1,
          "terminated": false,
          "truncated": false
        },
        {
          "state": 0,
          "action": "R",
          "next_state": 1,
          "reward": -1,
          "terminated": false,
          "truncated": false
        },
        {
          "state": 1,
          "action": "R",
          "next_state": 2,
          "reward": -1,
          "terminated": false,
          "truncated": true
        }
      ],
      "reward_sum": -4,
      "gamma": "9/10",
      "discounted_return": "-3439/1000"
    }
  },
  "handwritten_policies_not_learned": true,
  "real_world_actions": false
}