Sign inSign in
ConceptAI & ML

Model-based reinforcement learning

A reinforcement learning approach where an environment model is learned from data and then used for control or planning.
as Sergey Levine defines itUC BerkeleyThe wording closest to all 9 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.

  • David Silver

    Google DeepMind · Introductory

    Reinforcement learning where the first step is to build a model of how the environment works, and then plan with it.
    • 1:15:02Introduction to Reinforcement Learning
    • 7:16Integrating Learning and Planning
  • Sergey Levine

    UC Berkeley · Undergraduate

    A reinforcement learning approach where an explicit model of the environment dynamics is learned and used for planning actions.
    • 6:46Foundational concepts in deep reinforcement learning
    • 0:01Exploration of advanced topics in deep reinforcement learning
  • Pieter Abbeel

    UC Berkeley · Undergraduate

    An approach where data is collected from the environment to estimate the transition and reward functions, allowing standard MDP techniques to be reused.
    • 20:00Reinforcement Learning Part 1/2
    • 7:15Reinforcement Learning Part 2/2
  • Emma Brunskill

    Stanford University · Undergraduate

    Learning a model of the reward based on collected preference data and feedback.
    • 7:54Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
  • Andrea Zanette

    UC Berkeley · Graduate

    An approach where an agent tries to fit a model of the environment from data and uses it to make predictions and plan.
    • 53:43Towards a Statistical Foundation for Reinforcement Learning

Lectures that assume it

5

Connections

24

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

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.