{
  "schemaVersion": 1,
  "lessonId": "rl-04",
  "contentHash": "60ee26b667e26e302f7f6417e510aff429e2068da88b725c7268c907aa9f2a03",
  "rendererHash": "a1bd5b648f4731ae5d5f0a24811c2540d1a0a132149ce589d17c4113509cbedf",
  "kind": "executed",
  "generatedAt": "2026-10-20T10:46:27.202039+00:00",
  "provenance": "recorded_cpu_computation",
  "environment": {
    "backend": "cpu",
    "deviceCount": 1,
    "jax": "0.9.2",
    "numpy": "2.4.4",
    "matplotlib": "3.10.8"
  },
  "stdout": "training seeds: [0, 7, 23, 41, 59]\nheld-out mean per agent: [0.9759717  0.97472161 0.97537106 0.96944821 0.97455072]\nexact mean per agent: [0.97578394 0.9749347  0.97562152 0.97113729 0.97404611]\nuniform baseline mean: 0.46628910303115845\nacross-agent mean / sample sd: 0.9740126609802247 0.0026129212275767476\n",
  "data": {
    "kind": "bar",
    "labels": [
      "0",
      "7",
      "23",
      "41",
      "59"
    ],
    "xlabel": "training seed",
    "ylabel": "mean episode return",
    "series": [
      {
        "label": "held-out sampled",
        "y": [
          0.9759716987609863,
          0.9747216105461121,
          0.9753710627555847,
          0.9694482088088989,
          0.974550724029541
        ]
      },
      {
        "label": "exact expectation",
        "y": [
          0.9757839441299438,
          0.9749346971511841,
          0.9756215214729309,
          0.971137285232544,
          0.9740461111068726
        ]
      },
      {
        "label": "uniform baseline (shared)",
        "y": [
          0.46628910303115845,
          0.46628910303115845,
          0.46628910303115845,
          0.46628910303115845,
          0.46628910303115845
        ]
      }
    ]
  }
}