---
title: "Deep Q-Network"
created: 2026-04-15
updated: 2026-04-15
type: concept
tags: [rl, optimization]
sources: []
---

# Deep Q-Network (DQN)

Deep Q-Network (DQN) is a deep reinforcement learning value-based method that combines Q-learning with deep neural networks to learn policies directly from high-dimensional sensory input. Introduced by DeepMind in 2015, DQN achieved human-level performance on [[atari-2600]] games and established deep RL as a viable approach for complex decision-making tasks. It serves as a foundational algorithm referenced in [[policy-distillation]] research.

## Related

- [[policy-distillation]] — DQN policies were distilled in the original Policy Distillation paper
- [[atari-2600]] — Primary benchmark environment for DQN evaluation
- [[imitation-learning]] — Alternative paradigm to value-based RL

## References

- Mnih et al. (2015). "Human-level control through deep reinforcement learning." Nature 518.