Standard 8 stops to get here

Deep Q-Network

Combining Q-learning with deep neural networks to handle high-dimensional state spaces, enabling RL for complex tasks like Atari games.

Your route here

8 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Neural Network ✓ understood

    A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.

  3. Reinforcement Learning ✓ understood

    Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies.

  4. Reward ✓ understood

    The single number an environment sends back after each action, telling a reinforcement learning agent how good that step was; the agent learns to maximize its long-run total.

  5. Agent ✓ understood

    In reinforcement learning, the learner and decision-maker that observes an environment, takes actions and adjusts its behaviour to maximize cumulative reward.

  6. Policy ✓ understood

    The rule an RL agent uses to choose actions: a mapping from each state to an action, or to a probability distribution over actions.

  7. Value Function ✓ understood

    A function estimating expected cumulative reward from a state (state-value) or state-action pair (action-value/Q-value).

  8. Q-Learning ✓ understood

    A model-free RL algorithm that learns action-value functions (Q-values) to determine optimal actions in each state.

  9. Deep Q-Network · you are here ✓ understood

Where it sits

Deep Q-Network

Leads to

Nothing yet: a destination in its own right.

Explore nearby

In the research

All papers →

A paper that builds on Deep Q-Network .