Skip to content
Sign in

Reinforcement Learning

Playing Atari with Deep Reinforcement Learning

L4 · ExpertMnih, Kavukcuoglu, Silver, Graves, Antonoglou, Wierstra, Riedmiller · 2013 · NeurIPS Deep Learning Workshop 2013

TL;DR

Learns to play Atari games straight from raw pixels by combining Q-learning with a deep convolutional network, the Deep Q-Network (DQN).

Why it matters

DQN showed that deep networks could learn control policies end to end from high-dimensional input, launching modern deep reinforcement learning.

Key ideas

  • Approximate the action-value function Q with a convolutional network over pixels.
  • Experience replay stores past transitions and samples them to stabilize learning.
  • A separate, slowly-updated target network reduces feedback instability.
  • One architecture learned many games with the same hyperparameters.

Related concepts

reinforcement-learningdeep-learning
Read the paper on arXivLearn the concept