Home▸Cybersecurity▸AI Attack Path Planner 2D: Q-Learning on a Network Graph

AI Attack Path Planner 2D: Q-Learning on a Network Graph

A 2D top-down view of a reinforcement-learning agent teaching itself to break into a network: drag to pan the graph, watch Q-values converge edge by edge via the Bellman equation, and drag a defender-vigilance slider to see the learned path trade cost for detection risk.

Cybersecurity2DAdvanced60 FPS📱 Mobile-adapted⇄ 3D version

A reinforcement-learning agent explores a 2D graph of network hosts — from an internet-facing DMZ entry point through internal segments to a crown-jewel target — learning, hop by hop, which lateral-movement path best balances effort against the chance of tripping a defender's detection. Every edge updates its Q-value live via the Bellman equation, glowing brighter and thicker as the agent converges on a policy. Drag the canvas to pan the graph and scroll/pinch to zoom, while a reward sparkline and a per-edge Q-value bar chart along the bottom make the convergence measurable, not just visible. A defender-vigilance slider lets you watch the learned policy shift in real time as detection gets more expensive.

⚙ Under the hood

A pannable 2D view of a reinforcement-learning agent exploring a network graph from a DMZ entry point to a crown-jewel target, learning Q-values for every lateral-movement hop via the Bellman equation while a defender-vigilance slider changes the detection risk it must weigh against effort.

reinforcement learningq-learningcybersecurityattack graphai securitynetwork defense

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install