Sign inSign in
ConceptAI & ML

Partially observable Markov decision process

A POMDP is a generalization of a Markov decision process that adds unobserved states, observations, and an observation function where the agent maintains a belief state distribution over states.
as Pieter Abbeel defines itUC BerkeleyThe 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.

Lecturers

3

Each in their own terms, from the easiest level.

  • David Silver

    Google DeepMind · Introductory

    The formalism used when working with partially observable environments where the agent must construct its own state representation.
    • 52:36Introduction to Reinforcement Learning
  • Sergey Levine

    UC Berkeley · Graduate

    A POMDP is an MDP that has observations and observation probabilities in addition to states and actions.
    • 0:27Transfer Learning & Meta-Learning (CS 285, Lecture 22, Part 5)

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.