◀ VibeCruiser

multi agent reinforcement learning in congestion games

A free browser game — play it in your browser, no install. Exact atomic Braess analysis and deterministic multi-agent learning, presented as an interactive Three.js essay

by @mihirrao-10 · mihirrao-10/multi-agent-reinforcement-learning-in-congestion-games on GitHubLANG TypeScriptHOSTED ON MIHIRRAO-10.GITHUB.IOUPDATED 5 Oct 2026

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

Made this, @mihirrao-10? See how many people played it → or use email

Controls: Arrow keys

▶ 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

Live interactive essay · Experiment methodology · Study guide

Each episode represents a new morning commute. Independent tabular learners separately choose complete routes from source S to destination T, experience only their own trip, and update only their own selected action. They do not meet, message, or exchange Q-values. Their shared congestion couples their rewards without creating communication between learners. With the central link closed, an even split gives every commuter a 90-minute trip.

Read the full README on GitHub →

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

More like this

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 →