◀ VibeCruiser

q learning pong

A free pong game — play it in your browser, no install. Watch tabular Q-learning learn to play Pong, one generation at a time. Live: q-learning-pong.vercel.app

by @tamagusko · tamagusko/q-learning-pong on GitHubLANG JavaScriptHOSTED ON Q-LEARNING-PONG.VERCEL.APPUPDATED 23 Sep 2026

Vote and save it — free account with email or sign in with GitHub

Made this, @tamagusko? See how many people played it → or use email

Controls: Space

▶ Play full screen ▲ Vote: free account with email ▲ Or sign in with GitHub

GitHub may ask you to sign in, then to let VibeCruiser “Verify your GitHub identity” and “Act on your behalf”. We only read your profile and email, and never post anything.

Open the live demo Source on GitHub

From the README

Watch tabular Q-learning learn to play Pong, one generation at a time.

The loop, live. Observe the state, choose a move, receive a reward, update the table, with the real numbers from the game. Generations. The same agent after 0, 10, 20, 30, 50 and 100 training matches plays the same serve side by side. Any generation from 0 to 100 can be picked. The policy. A map of the best move in every row of the Q-table.

Training is 100 matches against a fixed opponent, with ε-greedy exploration falling from 0.7. It runs in the browser in a fraction of a second.

Read the full README on GitHub →

Built something like this? Submit your vibe — free account, takes a minute. How listing works.

More like this

More pong games →

Made this?

Claim it: create a free account, then press CLAIM THIS in the cruiser. Put the badge below in your README or on your demo page first; that link is how we know it's yours.

Your project is on the cruise, loaded live from your own site. Put the badge in your README or on the demo page: it shows your live play count, it links back to this page, and everyone who lands here is one click from running the real thing.

On VibeCruiser

How listing, the badge and claiming work →