Sign inSign in
ConceptAI & ML

Exploration

The strategy of trying unknown actions to gather information about the environment's dynamics and rewards.
as Pieter Abbeel defines itUC BerkeleyThe wording closest to all 8 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 learning6Decision making2Reward2Agent environment interaction1Exploitation1Information gathering1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

7

Each in their own terms, from the easiest level.

  • David Silver

    Google DeepMind · Introductory

    Doing something else to gather more information which might lead to better decisions in the long run.
    • 1:21:50Introduction to Reinforcement Learning
    • 2:52Exploration and Exploitation
  • Emma Brunskill

    Stanford University · Undergraduate

    Learning about the world through direct experience by making decisions where choices impact what is subsequently learned.
    • 19:37Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    The process of trying new actions to discover better strategies in reinforcement learning.
  • Ashish Vaswani, Lucas Beyer & William Fedus

    Stanford University · Graduate

    The process of seeking out unfamiliar parts of the state space, which is the opposite of exploitation.
    • 1:12:46Decision Transformer: Reinforcement Learning via Sequence Modeling
  • Sergey Levine

    UC Berkeley · Graduate

    Doing things you haven't done before in the hopes of getting even higher reward.
    • 5:58Foundational concepts in deep reinforcement learning
  • Onur Mutlu

    ETH Zürich · Graduate

    Taking actions that deviate from the current optimal policy to discover potentially better strategies.
    • 1:30:10Memory Controller Microarchitecture, Row Policies & Request Scheduling

Lectures that assume it

2

Connections

16

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

7 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.