Sign inSign in
ConceptAI & ML

Exploration vs. exploitation

The trade-off between choosing known actions that yield high rewards (exploitation) and trying new actions to discover potentially better ones (exploration).
as Onur Mutlu defines itETH ZürichThe wording closest to all 4 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.

Reinforcement learning2Optimization search strategies1Policy1Q-learning1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

4

Each in their own terms, from the easiest level.

  • Brian Yu

    Harvard University · Undergraduate

    The fundamental trade-off in reinforcement learning between choosing actions known to yield high rewards versus trying new actions to discover potentially better strategies.
    • 8:48:31Harvard CS50’s Artificial Intelligence with Python – Full University Course
  • Pieter Abbeel

    UC Berkeley · Undergraduate

    The dilemma of whether to try new untried actions to potentially learn better policies or to exploit current knowledge for immediate reward.
    • 17:00Reinforcement Learning Part 2/2
  • Robert Gramacy

    Virginia Tech · Graduate

    Exploitation uses current knowledge to move to the best nearby spot, while exploration investigates new or uncertain areas of the search space.
    • 33:04Surrogate Modeling and Bayesian Optimization (Part 2)

Lectures that assume it

2

Connections

11

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

4 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.