Path: csiph.com!eternal-september.org!feeder.eternal-september.org!.POSTED!not-for-mail
From: Intelli2 <intelli2@mama.com>
Newsgroups: comp.programming.threads
Subject: Towards Deep Symbolic Reinforcement Learning
Date: Mon, 13 Nov 2017 18:50:46 -0500
Organization: A noiseless patient Spider
Lines: 19
Message-ID: <oudb4n$2te$9@dont-email.me>
Mime-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Date: Mon, 13 Nov 2017 23:50:47 -0000 (UTC)
Injection-Info: reader02.eternal-september.org; posting-host="4604a184d92dddd74a88be09ef7ccba2"; logging-data="2990"; mail-complaints-to="abuse@eternal-september.org";	posting-account="U2FsdGVkX1/oAeIY2nL1YlkVlt8oZA3it0C/wKxMuiI="
User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.4.0
Content-Language: en-US
X-Mozilla-News-Host: news://news.eternal-september.org:119
Cancel-Lock: sha1:DcWE7IXA/NTnI159IxuQBK1ER4g=
Xref: csiph.com comp.programming.threads:3927

Hello,


Read this:

Here is another promising way to Artificial Intelligence, it combines 
neural network learning with aspects of classical symbolic AI, gaining 
the advantages of both methodologies without their respective
disadvantages, please read about it:


Towards Deep Symbolic Reinforcement Learning

https://arxiv.org/pdf/1609.05518.pdf



Thank you,
Amine Moulay Ramdane.