Sign inSign in
ConceptAI & ML

Q-learning

A reinforcement learning method that uses a function approximator to estimate the action-value function.
as Fei-Fei Li, Justin Johnson & Serena Yeung defines itStanford UniversityThe wording closest to all 6 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

5

Each in their own terms, from the easiest level.

  • Pieter Abbeel

    UC Berkeley · Undergraduate

    A model-free reinforcement learning algorithm that updates Q-value estimates using sample transitions and the max future Q-value.
    • 1:05:50Reinforcement Learning Part 1/2
    • 8:50Reinforcement Learning Part 2/2
  • David Silver

    Google DeepMind · Undergraduate

    An off-policy temporal-difference learning algorithm for estimating action-values without requiring importance sampling.
    • 1:28:51Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
  • Brian Yu

    Harvard University · Undergraduate

    A method for learning a function Q of s comma a that estimates the value of performing action a in state s.
    • 8:35:36Harvard CS50’s Artificial Intelligence with Python – Full University Course
  • Onur Mutlu

    ETH Zürich · Undergraduate

    A reinforcement learning method where an agent stores quality values for every state-action pair to determine the best action to take.
    • 13:56Prefetching II, Processing-in-Memory, and Parting Thoughts (ETH Zürich: Digital Design and Computer Architecture, Lecture 25)

Lectures that assume it

23

The first 12 are shown.

Connections

39

The lectures that define it or assume it, and the concepts next to it.

Concepts10

Show 4 more

Lectures29

Show 23 more

5 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.