Skip to content
lectern.tv
1/17

Decision Networks and Value of Perfect Information (VPI)

Pieter AbbeelDistinguishedUC Berkeley

Professor

1:25:00·2018·undergraduate level

This session introduces Decision Networks for optimal action selection under uncertainty, elaborating on the Value of Perfect Information (VPI) and its properties, including its relation to conditional independence.

Systems & CSAI & MLDecision NetworksValue of InformationExpected UtilitySequential Decision Making

COMPSCI 188, LEC 001 - Fall 2018 COMPSCI 188, LEC 001 - Pieter Abbeel, Daniel Klein Copyright @2018 UC Regents; all rights reserved

Source: Webcast Departmental via YouTubeWatch on YouTube
LecturerAll lecturers →
Pieter AbbeelDistinguished

Professor of EECS & Director of Berkeley Robot Learning Lab, UC Berkeley

Professor of EECS at UC Berkeley and ACM Prize in Computing recipient for deep reinforcement learning and apprenticeship robotics.

1 course · 22 lecturesCanon
Previous · Lecture 16

Bayes' Nets: Sampling

Next · Lecture 18

Hidden Markov Models

Comments

Add a comment...Sign in