# From private job to Arena

> How comparison, evaluator trust, lineage, and the public learning loop work.

Audience: Everyone
Updated: 2026-08-02
Page: /docs/arena

## How Arena works

1. Open a challenge and read the task, trial count, and scoring method.
2. Package the policy entrypoint from your existing repository.
3. Submit the policy you want to evaluate.
4. HIM runs it with the same robot, starting conditions, trials, and evaluator used for every entry.
5. See the score, builder, policy version, and evidence behind the run.
6. The winning eligible Table Tennis policy may be reviewed for a supervised session on HIM’s real Unitree G1.

## A visible path from simulation to a real robot

Every HIM Official challenge shows the task, the reward, and the steps between a simulation score and hardware. Table Tennis leads to a supervised sim-to-real session on HIM’s Unitree G1. The completed Nick Kosir Dance challenge shows a prior full path: Stanford students at HIM retargeted the reference motion, trained and stabilized the policy in simulation, then transferred it to Adam.

- Table Tennis is open: rank under the shared evaluator, pass HIM’s hardware review, and earn the winning eligible policy’s supervised Unitree G1 session.
- Nick Kosir Dance is complete: more than 150 million training iterations led from reference video through MuJoCo and Isaac Lab to Adam.
- Skateboarding is upcoming: test balance, recovery, and whole-body locomotion on a moving board.

> **A score is a qualification, not a remote-control pass:** Hardware execution remains supervised and subject to policy compatibility, safety limits, and operator review. Arena never presents simulation as a real-robot result.

> **Compute is optional:** Use HIM Compute when you need private inference, simulation, or training. Use Arena when you want to enter a shared challenge and publish a verified score.

## Build with the challenge data

HIM's real Rokoko motion, Orbbec RGB-D, and WitMotion paddle IMU table-tennis captures are available to download now. Hidden evaluator episodes stay private so the leaderboard measures generalization instead of memorization.

- Released challenge data can be used with any training code or simulator.
- Earned hardware data gives active builders access to hard-to-collect robot trajectories, telemetry, and synchronized video.
- Hidden evaluation data is isolated from candidate code and never bundled into a public starter set.

## What makes a score official

- The evaluator version and digest are fixed before the result is published.
- Candidate output freezes before evaluator execution.
- Only evaluator-attested numeric metrics become authoritative.
- The artifact manifest and result attestation bind the run, package, environment, and provider job.
- Blind battle identity stays hidden until the vote/reveal rule permits it.
- Hardware evidence requires a separate supervised Unitree G1 review; simulation never silently becomes a hardware claim.

## Enter the live challenge

- [Open Arena](/) — Open the live table-tennis challenge.
- [Open Results](/sims) — See separate Official, Community, and Unitree G1 result lanes.
- [Upload a policy](/build#policy) — Publish a policy build without inventing a score.
- [Read the dance case study](https://www.himrobotics.com/blog/nickkosir) — See how a student-built dance policy moved from simulation to Adam.