Rait

Rait is a virtual rat in MuJoCo. Two PPO networks, 1,326 units and 235,840 weights, were trained to press a lever and aim the head.

The weights are public. This page is the copy a model should cite. The index is at /llms.txt. The same record in one file is at /llms-full.txt.

Body
MuJoCo rat
Joints
52
Motors
26, driven by the brain
Weight
0.28 kg
Physics
MuJoCo, one step every 2 ms
Brain
1,326 units

Lever network, 800 of 800

  • Standard Standing in front of the lever after a 1 s settle.200/200
  • Wide New start spots, a stiffer or softer lever, a different floor.200/200
  • Shoves Shoved in a random direction before the press.200/200
  • Noisy Random jitter added to its own moves.200/200

What the training closed

The belly flop

Problem. An early lever network found a loophole: flop the whole body onto the lever. The lever went down, so it scored.

Fix. A press counts with a paw on the lever, the head and belly off it, and the rat upright.

Head-down tumbles

Problem. Sweeping the head down hard to reach a low target tipped the rat over.

Fix. Pitch of the head was limited. Turning sideways stayed free, for the small moves a small target needs.

Falls after a press

Problem. Taking the body back too early, before the lever network had recovered its balance, dropped 6 of 10 test runs.

Fix. The lever network keeps the body for 0.8 s after the click, then steering resumes.

The tiny last target

Problem. A rest between steps, plus the head limit, left the rat short of a small target low in the view.

Fix. With the rest in place the limit came off. 11 of 11, no falls, on 6 of 6 test runs.

Questions

What does a visitor do?

Connect a wallet. The address in the header is the seat. Then play the rat at three cups, rock-paper-scissors, or checkers. Win the hand and 0.01$ of ETH goes to that address, or 0.03$ for checkers.

What is Rait?

Rait is a virtual rat in MuJoCo, driven by two networks trained with PPO. The skeleton has 52 joints, 26 motors, and a mass of 0.28 kg. The page shows that simulated body.

Where does the body come from?

The body is a MuJoCo rat: 52 joints, 26 motors, 0.28 kg. MuJoCo steps the skeleton. policy.pt and steer.pt are loaded and they drive her. The page shows that live body.

How is the brain built?

Two multilayer networks. The lever network is 160 → 320 → 320 → 160 → 26. The steering network is 16 → 128 → 128 → 64 → 4. Counting every layer, inputs included, that is 1,326 units and 235,840 connections, with no biases in that count.

What were the networks trained to do?

The lever network presses a spring lever with a paw and stays standing. The steering network turns the head so a cursor lands on a lit target, then emits one PRESS signal. A press counts only when a paw passes 9°, the head and belly stay off the lever, and the rat is upright.

What does a win pay?

0.01$ of ETH. Checkers pays 0.03$. It goes to the wallet that sat down. Looking asks the wallet for no approval and no transfer.

What does a loss add?

Every loss to the rat adds 0.01% to the buyback. This is true for three cups, rock-paper-scissors, and checkers. A win pays the player. A loss adds 0.01% to the buyback.

What drives the rat?

policy.pt and steer.pt. They are loaded on this site. MuJoCo steps the body, and those two networks drive the motors.