All drills

Learn Fast: Autonomous Agents on FrozenLake

What you'll be able to do

Build an agent that learns by trial and error to reach a goal — the core loop behind game AI, robotics, and control.

The trial-and-error loop behind game-playing agents (DeepMind, OpenAI), warehouse-robot navigation (Amazon), and self-driving (Waymo) — trained in simulators like NVIDIA's.
Start this internship
Create an account to unlock the 4 sections, the workbench, and AskThili.
Begin

Sections

1. Learn Fast: Autonomous Agents on FrozenLake
🔒 locked
2. Autonomous Agents
🔒 locked
3. Q-Learning and the Random Agent
🔒 locked
4. UI Application
🔒 locked

Dig deeper

📄Technical Note: Q-Learning (Watkins & Dayan, 1992)
paper
🔗FrozenLake — Gymnasium docs
article

Part of these learning paths

I'm a software engineer and I want to learn agentic programming
View path →