Location: Conferences » Other » Large-scale Online Learning and Decision Making (LSOLDM) Workshop, Cumberland Lodge 2012

Online Reinforcement Learning from Concurrent Customer Interaction Sequences

author: David Silver, Department of Computer Science, University College London
published: May 28, 2013,   recorded: September 2012,   views: 4171
Categories

See Also:

Help icon Streaming Video Help

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.
  Delicious Bibliography

Description

This talk explores applications in which a company interacts with many customers. The company has an objective function, such as maximising revenue, customer satisfaction, or customer loyalty, which depends primarily on the sequence of interactions between company and customer. A key aspect ofthis setting is that interactions with different customers occur asynchronously and in parallel. As a result, it is imperative to learn online from partial interaction sequences, so that information acquired from one customer is efficiently assimilated and applied in subsequent interactions with other customers. I will present the first framework for reinforcement learning in this setting, using an asynchronous variant of temporal-difference learning to learn efficiently from partial interaction sequences.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Lars Rigter, November 10, 2017 at 10:39 a.m.:

Dear Mr Silver,
I have a question about the concurrent reinforcement learning algorithm.
What if one customer likes to receive a lot of newspapers and another customer really does not like to receive a newspaper at all. Will the algorithm be able to customize it for both customers or will it concurrently learn from the first customer to sent a lot of emails to the other customer as well.

Thank you in advance.

Best Regards,

Lars Rigter

Comment2 Carl Marx, October 15, 2018 at 8:03 a.m.:

It is challenging for the customers and their re-enforcement and anyone can convert them as per customers requests.

Watching all these lectures with Moviebox is easier and safe. You can stream videos from mobile and learn from them.

https://movieboxbuzz.com/download-mov...

Comment3 moviebox, December 14, 2018 at 11:47 a.m.:

Thanks lot for your video guided tutorial. This kind of Movie related guides will be so much help to everybody.
I am using MovieBox to download & watch my favorite Moves, this is also really my interesting application.

Comment4 jana, December 14, 2018 at 11:50 a.m.:

Thanks lot for your Guide... https://moviebox.mobi/

Comment5 John Claves, March 13, 2019 at 9:06 a.m.:

Great Post

https://toptechtalk.kinja.com/best-al...

Comment6 workspace login com, June 22, 2019 at 1:49 p.m.:

Thank you for proving this useful and informative information. By this information, I get very much help and resolve my problem.

Comment7 Mark, July 26, 2019 at 8:04 a.m.:

Thank you for the post.
https://vavoo-tv.com/

Comment8 Ana, December 27, 2019 at 5:02 p.m.:

nice post, good work.
From admin <a href="https://gbmod.net/download-gbwhatsapp-apk/">Gbwhatsapp apk</a>...

Write your own review or comment:

make sure you have javascript enabled or clear this field: