{
  "schema_version": 5,
  "model_api": 1,
  "name": "microduck-running",
  "kind": "perpetual",
  "obs_len": 61,
  "action_len": 14,
  "action_scale": 1.0,
  "entry_pose": "standing",
  "duration_s": null,
  "status": "simulation-only-hardware-candidate",
  "description": "Robustified iteration-12195 forward-running policy for the stock MicroDuck on flat ground. It is not hardware validated.",
  "command": {
    "layout": "twist(3), head_pose(4), body_pose(6)",
    "twist": [
      "forward velocity command in m/s; curriculum trained through 2.2; evaluated at 2.2; not a hard speed limit",
      "lateral velocity; use 0 (training range was only -0.02 to 0.02 m/s)",
      "yaw rate; use 0 (training range was only -0.05 to 0.05 rad/s)"
    ],
    "head": "unused; zeros",
    "body": "unused; zeros",
    "idle": [0, 0, 0],
    "exact_zero_training_fraction": 0.03
  },
  "robot": {
    "model": "microduck",
    "hw_rev": 1,
    "servos": "14x Dynamixel XL330",
    "control_hz": 50,
    "hardware_modifications_required": false
  },
  "training": {
    "task_id": "Mjlab-Running-Flat-MicroDuck",
    "algorithm": "PPO (rsl_rl)",
    "repo": "Vottivott/microduck-playground",
    "commit": "828d950134e29a8d04cbb51720a22c8729047fb7",
    "upstream_base": "pollen-robotics/microduck_rl@d424a0c899f6b33cbd3daeb279913134349c0b63",
    "checkpoint_iteration": 12195,
    "resumed_from": "iteration 11748",
    "num_envs": 4096,
    "seed": 42,
    "common_environment": {
      "MICRODUCK_RUNNING_TARGET_MAX_SPEED": 2.2,
      "MICRODUCK_RUNNING_SPEED_CAP": 2.4,
      "MICRODUCK_RUNNING_ACTION_RATE_WEIGHT": -0.1,
      "MICRODUCK_RUNNING_HIGH_SPEED_STAGE_INTERVAL": 750,
      "MICRODUCK_RUNNING_FORWARD_PROGRESS_WEIGHT": 5.0,
      "MICRODUCK_RUNNING_ENABLE_SYMMETRY": false,
      "MICRODUCK_RUNNING_ENABLE_HEADING_FEEDBACK": false,
      "foot_friction_range": [0.7, 1.3],
      "push_interval_s": [3.0, 6.0]
    },
    "robustification_stages": [
      {"updates": 100, "push_m_s": 0.03, "trunk_com_m": 0.003, "head_com_m": 0.003, "initial_tilt_deg": 1.0},
      {"updates": 150, "push_m_s": 0.06, "trunk_com_m": 0.005, "head_com_m": 0.005, "initial_tilt_deg": 1.5},
      {"updates": 200, "push_m_s": 0.1, "trunk_com_m": 0.008, "head_com_m": 0.006, "initial_tilt_deg": 2.0}
    ],
    "export": "scripts/export.py; observation normalizer baked into policy.onnx",
    "continuation_checkpoint": {
      "path": "checkpoint.pt",
      "sha256": "052f6df6683fdae83deb369b7f2c7d13e45f87ed2907adee6e23b1ebf9dfe973",
      "actor_exact_to_released_onnx": true,
      "original_full_ppo_state": true
    }
  },
  "eval": {
    "sim_proxy": "mjlab / MuJoCo Warp with BAM XL330 M6 actuator model",
    "command_speed_m_s": 2.2,
    "duration_s": 10.0,
    "warmup_s": 1.0,
    "results": {
      "nominal_plain": {"num_envs": 512, "speed_m_s": 1.6510932445526123, "survival": 0.9921875},
      "stress_plain": {"num_envs": 512, "speed_m_s": 1.6349653005599976, "survival": 0.98828125},
      "nominal_backlash": {"num_envs": 256, "speed_m_s": 1.6362495422363281, "survival": 0.98828125},
      "stress_backlash": {"num_envs": 256, "speed_m_s": 1.6121970415115356, "survival": 0.984375},
      "high_grip_stress": {"num_envs": 512, "speed_m_s": 1.6424154043197632, "survival": 0.966796875}
    },
    "stress": {"push_m_s": 0.1, "trunk_com_m": 0.01, "head_com_m": 0.006, "initial_tilt_deg": 2.0},
    "known_limits": "Heading and lateral drift remain substantial. Never tested on hardware."
  },
  "onnx_contract": {
    "observation_normalizer_embedded": true,
    "training_action_clipping": false,
    "onnx_output_clip": false,
    "checkpoint_parity_max_abs_error": 0.00000762939453125
  },
  "sim2real": {
    "retained": [
      "BAM XL330 M6 voltage control, back-EMF, current limiting, battery 6.5-8.2 V, and load-dependent sag",
      "3-6 physics-step actuator delay, 0-1-step IMU delay, and one-control-step joint-velocity lag",
      "foot friction 0.7-1.3",
      "trunk mass/inertia +/-5%, trunk CoM +/-8 mm, head CoM +/-6 mm, armature +/-10%, and BAM joint friction +/-10% in the final training stage",
      "planar velocity pushes up to +/-0.10 m/s and initial pitch/roll up to +/-2 degrees in the final training stage",
      "encoder bias +/-0.015 rad, IMU misalignment up to 6 degrees, and actor observation noise"
    ],
    "relaxed": [
      "flat terrain only",
      "trained on the ordinary non-backlash robot model; backlash is cross-evaluation only",
      "head/body pose-command widening curricula removed",
      "weaker posture, angular-motion, foot-slip, and action-rate regularization; head/body pose tracking disabled",
      "motor-gain randomization remains disabled in the inherited recipe"
    ],
    "hardware_validated": false
  },
  "versions": {
    "default": {"iteration": 12195, "policy": "policy.onnx", "checkpoint": "checkpoint.pt", "preview": "media/preview.mp4"},
    "speed_parent": {"iteration": 11748, "directory": "lineage/iteration-11748"},
    "legacy_mat_policy": {"iteration": 8749, "directory": "legacy/iteration-8749"}
  },
  "media": {
    "preview": "media/preview.mp4",
    "run_into_mat": "media/run-into-mat.mp4",
    "run_into_mat_policy_iteration": 8749,
    "run_into_mat_note": "The mat, collision augmentation, camera treatment, motor cutoff, and sparks are scripted demo elements. The policy has no obstacle perception.",
    "audio": false
  },
  "source_artifact_sha256": "007707dd7779b2756ded67c58b2e9f94fe5071794a48c2b5a20d5f8d841efbeb",
  "artifacts": {
    "policy_onnx_sha256": "007707dd7779b2756ded67c58b2e9f94fe5071794a48c2b5a20d5f8d841efbeb",
    "checkpoint_pt_sha256": "052f6df6683fdae83deb369b7f2c7d13e45f87ed2907adee6e23b1ebf9dfe973",
    "preview_mp4_sha256": "942f0802cc0c6795769bd99a9991f866fee682890ea9ea6d71077f7d4eb5492b"
  }
}