Sign inSign in
ConceptSystems & CS

ϵ\epsilon-greedy algorithm

An algorithm that mostly acts greedily with probability 1−ϵ1 - \epsilon while selecting a random action with probability ϵ\epsilon, resulting in linear total regret.
as David Silver defines itGoogle DeepMindThe wording closest to all 3 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

3

Each in their own terms, from the easiest level.

  • David J. Malan

    Harvard University · Introductory

    An algorithm where a small probability epsilon determines whether to make a random move or choose the highest-valued option.
    • 41:37Artificial Intelligence
  • Brian Yu

    Harvard University · Undergraduate

    A strategy for balancing exploration and exploitation by choosing the best estimated move most of the time while occasionally taking random exploratory actions with probability ϵ\epsilon.
    • 8:49:18Harvard CS50’s Artificial Intelligence with Python – Full University Course

Connections

8

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

3 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.