← 🤖 AI & Machine Learning

🧠 Q-Learning Agent

Episode: 0
Step: 0
Episode reward: 0
Best reward so far:
FPS:
Drag — rotate · Scroll — zoom

🧠 Reinforcement Learning: Q-Learning Agent

A robot agent explores a 3D grid world with no map, only trial, error, and reward — building a Q-table of state-action values that reshapes the terrain into a visible value-function landscape as learning progresses.

🔬 What It Demonstrates

The core reinforcement learning loop — agent, state, action, reward — and how the Q-learning update rule propagates value backward from the goal tile through the grid, one visited tile at a time.

🎮 How to Use

Adjust learning rate, discount factor, and exploration rate, then watch the agent's episode reward and value-function heatmap evolve live. Switch to policy view to see the greedy action chosen at every tile.

💡 Did You Know?

Q-learning, introduced by Chris Watkins in 1989, needs no model of the environment at all — it learns purely from experienced (state, action, reward, next state) tuples, which is why it scales to problems far too complex to hand-code, like Atari games and robotic control.