Back to lab

Preface

This is primarily for an assignment in Machine Learning Engineering, so it will not be very pedagocial. Still, I think this is fun to play around with, so maybe you’ll get inspiration to learn a bit about machine learning!

This idea was inspired by this video by Pezzza’s work!

Loading neural policy…
Distance3.16 m
Speed0.00 m/s
Reward / step+0.000
Flight time0.0 s

Choose method

Switch checkpoints to see what the same network learned at different points in training.

Controls

Thrust0.00
Rotational torque+0.00
Clockwise −1+1 Counterclockwise

The rocket accelerates along its nose. Braking means turning the engine against its motion. This is a spacecraft simulation, with no gravity.

Set a challenge

In neural and hand-written modes, arrow keys place the target when the flight area has focus. Space pauses. Every checkpoint starts from the same flight state when selected.

Move your pointer across the flight area, or drag the target on a touchscreen.

What does the network know?

Inputs

Δx / 3
+1.00
Δy / 3
+0.33
vₓ / 3
+0.00
vᵧ / 3
+0.00
sin θ
+0.89
cos θ
-0.45
ω / 6
+0.00

Position and velocity are relative to the flight frame. The angle is encoded as sine and cosine so a full turn does not create a numerical jump. The actor runs in your browser; it is not learning from your pointer.

What counts as a good move?

Rewards

Moving closer
+0.000
Distance penalty
+0.000
Staying close
+0.000
Speed near target
+0.000
Fuel penalty
+0.000
Turning & spin
+0.000

These terms sum to the live reward per simulation step. The learning algorithm optimizes reward accumulated over time, so a brief negative reward can still be part of a useful braking maneuver.