Q-Learning Gridworld

Reinforcement learning learns by reward. Watch an agent discover the best route through a gridworld — toward the goal, around the trap.

Q-Learning GridworldLive

learning to reach a goal

Controls

Presets

Discount factor γ

Step reward

Reinforcement learning finds a policy — an arrow in every cell — that maximizes long-term reward. A high discount γ makes the agent value the distant goal; a costlier step reward pushes it to take the shortest path. The colors show each cell's learned value. Educational tool.

▶ Run in Python

Data Inspector

Discount γ0.90

Start-cell value0.09

Behaviorcautious path

Governing equation

Q (s, a) \leftarrow Q (s, a) + α [r + 0.90 a^{'} max Q (s^{'}, a^{'}) - Q (s, a)]

Reading this result: With γ=0.9 and a mild step reward, the agent balances path length against reaching the goal, favoring a steady route.

Runs locally in your browser — free forever. Scale to the cloud when reality gets heavy.

or unlock everything with Pro →

★ Sign in to save this setup

Save your tuned setup, or drop this simulation into your own site, docs, or course page.

How it works

Q-learning estimates the long-term value of each action and derives a policy that maximizes cumulative reward. The discount factor sets how much the agent values the distant goal, and the per-step cost pushes it toward efficient paths. The arrows show the learned optimal policy. Educational tool.

✦

Ask the AI about this model

The math, the assumptions, real-world uses, or a code translation — explained for this exact simulation.

More CS / AI simulations

A* Pathfinding Maze Generator Neural Network k-Means Clustering Convex Hull L-System Fractals Turing Machine Image Convolution

Frequently asked questions

Is this q-learning gridworld simulator tool really free?▾

Yes. Q-Learning Gridworld runs entirely in your browser using your device's own compute, so local use is free forever. You only pay Compute Tokens if you scale a job to the cloud.

Do I need to install anything?▾

No. Everything runs client-side in a modern browser — no downloads, no license, no account required to start.

Can I save or share my simulation?▾

Create a free account to save projects, and use a shareable embed or minted DOI to publish a live, interactive version anywhere.

How accurate are the results?▾

The solver uses established numerical methods, but results are for research and educational purposes and should be validated against experiment or professional review before you rely on them.