Velociraptor Model
A dinosaur-inspired bipedal simulation model with actuated sickle-claw geoms, trained for locomotion and target-contact tasks. Its manifest (configs/velociraptor/stages.toml) declares three published behaviors on one trunk: stance (stand), locomotion (walk, warm-started from stance) and behavior (hunt — the strike task, warm-started from locomotion). See Behavior Recipes.
Generated specifications
These values are generated from the environment and compiled MJCF model. “Dynamic mass” is a simulator property, not an anatomical weight estimate.
| Gait | Bipedal |
|---|---|
| Observation dimension | 70 |
| Action dimension / actuators | 22 |
| Generalized coordinates (nq) | 31 |
| Generalized velocities (nv) | 30 |
| Compiled dynamic model mass | 13.5 kg |
| Plant contract revisions | Policy r10 · physics r2 · visual r3 |
| Model | environments/velociraptor/assets/raptor.xml |
Current curriculum configuration
The Stable-Baselines3 budgets and early-advancement gates below come from the current TOML files and can differ from older published runs. A stage also ends when its configured budget is exhausted. The recipe column names the behavior a stage belongs to and whether its checkpoint is a published deliverable; the warm-start column names the stage it starts from.
| Stage | Recipe | Warm-start from | Objective | SB3 configured budget | SB3 early-advancement gate |
|---|---|---|---|---|---|
| 1 — Balance | stand (deliverable) | — | Learn to stand and balance without falling | 6M | reward ≥ 1,050; episode length ≥ 950; ≥ 10 episodes/evaluation; 3 consecutive passes |
| 2 — Locomotion | walk (deliverable) | 1 — Balance | Learn forward walking/running | 8M | reward ≥ 100; episode length ≥ 750; avg. velocity ≥ 2 m/s; ≥ 10 episodes/evaluation; 3 consecutive passes |
| 3 — Strike | hunt (deliverable) | 2 — Locomotion | Sprint and strike prey with sickle claw | 12M | reward ≥ 100; task success ≥ 50.0%; ≥ 10 episodes/evaluation; 3 consecutive passes |
Backend-specific task-success semantics
- Stable-Baselines3 — Sickle-claw contact success: A left or right sickle-claw geom contacts the prey geom while the strike reward is enabled.
- JAX/MJX — Sickle-claw proximity success: Either claw-tip site comes within 0.20 m of the prey target position while the strike bonus is enabled; physical geom contact is not required.
Per-deliverable success semantics
- stand (1 — Balance) · Stable-Baselines3 — Reward-gated stance (reward_and_length/v1): The stance checkpoint clears the reward_and_length/v1 gate: mean evaluation reward at or above the statue-derived collapse rail and a near-full-horizon mean episode length over the required consecutive evaluations. The zero-action statue clears this gate, so stand is labelled by its gate kind here rather than claimed as certified stance quality; stance_quality/v1 waits on a foot-sensor repair (the single toe site reads about 55% of true load) (plan §4.8).
- walk (2 — Locomotion) · Stable-Baselines3 — Gated forward velocity (reward_and_length/v1): The locomotion checkpoint clears the reward_and_length/v1 gate: mean forward velocity at or above the stage's configured minimum, with its reward and episode-length floors, over the required consecutive evaluations.
- hunt (3 — Strike) · Stable-Baselines3 — Sickle-claw contact success: A left or right sickle-claw geom contacts the prey geom while the strike reward is enabled.
- hunt (3 — Strike) · JAX/MJX — Sickle-claw proximity success: Either claw-tip site comes within 0.20 m of the prey target position while the strike bonus is enabled; physical geom contact is not required.
Published run summaries
These are historical experiment records. A result is not evidence for the current model revision unless its provenance is explicitly marked current and verified.
PPO · Stable-Baselines3 · 2026-03-15
Provenance: Historical model · unverified · evaluation episode count not recorded · Stable-Baselines3 (version not recorded)
| Stage | Trained steps | Best eval reward | Avg. forward velocity | Task success (Stable-Baselines3) | Passed |
|---|---|---|---|---|---|
| 1 — balance | 6M | 1964.43 | 0.11 m/s | — | passed retired gate (reward gate) |
| 2 — locomotion | 8M | 2678.68 | 3.47 m/s | — | passed retired gate (reward gate) |
| 3 — strike | 8M | 1366.19 | 2.02 m/s | 93.3% | passed retired gate (reward gate) |
Current Stable-Baselines3 definition for this task label: A left or right sickle-claw geom contacts the prey geom while the strike reward is enabled.
SAC · Stable-Baselines3 · 2026-03-21
Provenance: Historical model · unverified · evaluation episode count not recorded · Stable-Baselines3 (version not recorded)
| Stage | Trained steps | Best eval reward | Avg. forward velocity | Task success (Stable-Baselines3) | Passed |
|---|---|---|---|---|---|
| 1 — balance | 6M | 970.19 | -0.64 m/s | — | passed retired gate (reward gate) |
| 2 — locomotion | 8M | 2078.62 | 2.91 m/s | — | passed retired gate (reward gate) |
| 3 — strike | 8M | 1195.43 | 1.63 m/s | 90.0% | passed retired gate (reward gate) |
Current Stable-Baselines3 definition for this task label: A left or right sickle-claw geom contacts the prey geom while the strike reward is enabled.
Anatomy
- Torso - Elongated body with simplified head/neck
- Legs - Digitigrade hind limbs (hip pitch/roll, knee, ankle, 2 toe digits per leg)
- Sickle claws - Actuated claw geom on digit 2 of each foot
- Arms - Stub forelimbs with shoulder pitch/roll actuators
- Tail - 5-segment counterbalance (4 actuated segments)
Diagnostic Metrics (behavior node, hunt)
After each training stage the eval command reports:
| Metric | Description |
|---|---|
mean_forward_velocity | Average forward speed (m/s) |
gait_symmetry | Left/right stride symmetry ∈ [0, 1] |
stride_frequency | Step frequency (Hz) |
cost_of_transport | Energy efficiency (lower is better) |
mean_pelvis_height | Upright stability (m) |
mean_heading_alignment | cos θ toward prey ∈ [-1, 1] |
success_rate | Fraction of episodes with successful sickle-claw target contact |
min_prey_distance | Closest approach to prey (m) |
Training Videos
Published videos for Velociraptor Mongoliensis, where available. Artifact provenance is shown on each stage.
Balance
Learn to stand and balance without falling
PPO · Stable-Baselines3 artifact · historical model · unverified · backend version not recorded. It is not evidence for the current model or stage config.
Locomotion
Learn forward walking/running
PPO · Stable-Baselines3 artifact · historical model · unverified · backend version not recorded. It is not evidence for the current model or stage config.
Strike
Sprint and strike prey with sickle claw
PPO · Stable-Baselines3 artifact · historical model · unverified · backend version not recorded. It is not evidence for the current model or stage config.
Usage
cd environments/velociraptor
# View the model
python scripts/view_model.py
# Train the stance node using its current TOML-configured budget
python scripts/train_sb3.py train --stage 1
# The advancing stages (stance, locomotion, behavior) in manifest order
python scripts/train_sb3.py curriculum --algorithm ppo
# Reuse an earlier run's certified stance and walk; train hunt in a fresh directory
python scripts/train_sb3.py curriculum --algorithm ppo \
--trunk-from logs/<earlier_run> --output-dir logs/<new_run>
See Behavior Recipes for the notebook workflow.