⚔️ Adam vs RMSprop Visualizer

Same landscape, same starting point — watch momentum change everything.

📋 How To Use This Lab
  1. Press Next Step ▶ — both balls take one REAL optimizer step, computed live.
  2. Watch the red RMSprop trail zigzag as it reacts only to the current gradient's size.
  3. Watch the green Adam trail glide smoothly — its momentum (β1) remembers where it was heading.
  4. Use Auto Run to race them all the way down and see who actually gets closer to the bottom.
Step 0
RMSprop loss = 2.004
Adam loss = 2.004
The Ravine — Two Valleys Joined by a Flat Saddle

🔴 RMSprop — divides by past squared gradients

v = β2·v + (1-β2)·g²
x -= lr · g / (√v + ε)

🟢 Adam — ALSO adds momentum on top

m = β1·m + (1-β1)·g  ← the extra step
v = β2·v + (1-β2)·g²
x -= lr · m̂ / (√v̂ + ε)
⚔️ RIVALPress Next Step — I'll move both balls using their real, actual update rules.
🧑‍🏫 PROF. TORCHAdam is basically RMSprop plus one extra idea: remember which way you were already moving.