{
  "schema_version": 1,
  "evaluation_type": "single_trained_policy_multiple_evaluation_seeds",
  "generated_at_utc": "2026-09-07T03:01:09.935197+00:00",
  "policy_file": "policy.onnx",
  "policy_sha256": "82a2369fe642eda505ee6d60c7ed26aafd177eb7484030834cd04e5a53035213",
  "training_seed": 42,
  "source_checkpoint": "model_3999.pt",
  "protocol": {
    "task_id": "Mjlab-Velocity-Flat-MicroDuck",
    "evaluation_seeds": [
      100,
      101,
      102,
      103,
      104,
      105,
      106,
      107,
      108,
      109
    ],
    "num_seeds": 10,
    "steps_per_seed": 400,
    "commanded_forward_velocity_mps": 0.5,
    "rendering": false,
    "video_generated": false,
    "policy_runtime": "onnxruntime-cpu",
    "actions": "deterministic"
  },
  "per_seed": [
    {
      "seed": 100,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14128163651563228,
      "mean_forward_velocity_mps": 0.23589461453258992,
      "mean_absolute_velocity_error_mps": 0.2643511279672384,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 101,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14869166431948544,
      "mean_forward_velocity_mps": 0.27104998455848545,
      "mean_absolute_velocity_error_mps": 0.23166746033821256,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 102,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14602043539285658,
      "mean_forward_velocity_mps": 0.2245279321074486,
      "mean_absolute_velocity_error_mps": 0.2757411253452301,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 103,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14819012811407448,
      "mean_forward_velocity_mps": 0.29148244574753335,
      "mean_absolute_velocity_error_mps": 0.2116375322631211,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 104,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14435075111687184,
      "mean_forward_velocity_mps": 0.22676853544602638,
      "mean_absolute_velocity_error_mps": 0.273739144433639,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 105,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14471292811096645,
      "mean_forward_velocity_mps": 0.22117613712325693,
      "mean_absolute_velocity_error_mps": 0.2788238628767431,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 106,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14796128492802382,
      "mean_forward_velocity_mps": 0.2755377550085541,
      "mean_absolute_velocity_error_mps": 0.22814512956538238,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 107,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.15238978615030646,
      "mean_forward_velocity_mps": 0.24962244590977206,
      "mean_absolute_velocity_error_mps": 0.2504566774680279,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 108,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.14997595064342023,
      "mean_forward_velocity_mps": 0.28972968977410346,
      "mean_absolute_velocity_error_mps": 0.21514052021782845,
      "termination_count": 0,
      "success_no_termination": true
    },
    {
      "seed": 109,
      "rollout_steps": 400,
      "commanded_forward_velocity_mps": 0.5,
      "mean_reward_per_step": 0.1540444320999086,
      "mean_forward_velocity_mps": 0.29541337831818965,
      "mean_absolute_velocity_error_mps": 0.2067692495981464,
      "termination_count": 0,
      "success_no_termination": true
    }
  ],
  "summary": {
    "mean_reward_per_step": 0.1477618997391546,
    "std_reward_per_step_population": 0.0036446650806754564,
    "mean_forward_velocity_mps": 0.258120291852596,
    "std_forward_velocity_mps_population": 0.02831245410335961,
    "mean_absolute_velocity_error_mps": 0.24364718300735694,
    "std_absolute_velocity_error_mps_population": 0.026886847320684554,
    "total_terminations": 0,
    "successful_seeds_no_termination": 10,
    "success_rate_no_termination": 1.0
  },
  "limitations": [
    "This evaluates one policy trained with seed 42; it does not measure training-seed variance.",
    "The test covers one fixed forward command and simulation only, not physical hardware."
  ]
}