← All drills

Learn Fast Deep Q Learning

What you'll be able to do

Recreate DeepMind's Atari-playing approach — deep RL for sequential decisions like games, routing, and control.

⌁ Game-playing agents (DeepMind Atari/Agent57), recommenders, datacenter/energy optimization, robotics, and ad bidding.
Start this internship
Create an account to unlock the 6 sections, the workbench, and AskThili.
Begin

Sections

1. Learn Fast Deep Q Learning
🔒 locked
2. Introduction
🔒 locked
3. Deep Q Learning
🔒 locked
4. Experience Replay
🔒 locked
5. Target Network
🔒 locked
6. Training a Deep Q Learning Model with RL Libraries
🔒 locked

Dig deeper

📄Playing Atari with Deep Reinforcement Learning (Mnih et al., 2013)
paper
📄Human-level control through deep reinforcement learning (Mnih et al., 2015, Nature)
paper
🔗Deep Reinforcement Learning — Google DeepMind
article