[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Additional reading for Reinforcement learning
- To: Rao Kambhampati <rao@asu.edu>
- Subject: Additional reading for Reinforcement learning
- From: Subbarao Kambhampati <rao@asu.edu>
- Date: Mon, 5 Oct 2009 16:43:48 -0700
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:sender:received:date :x-google-sender-auth:message-id:subject:from:to:content-type; bh=qTqaQnLf3iTzisdzEKwtqtBCz3eVe0mu8biubvHSar8=; b=TQfnXgchEN4ejkOZyAkWn9HCYpv4uCYEqsgkevxS2rq4ZwQ9Zr4jwHXyEDc04V+k8C cfxjpQKXcFwZ3P9ybMJ6safWs9El8iNGLRwtrwdGzq4fuZXgKc2kiiLctLyCuiocze4+ BjuWcHZCb6TTbr1uyPSlvv2GajuNJ/7A9dpFU=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:date:x-google-sender-auth:message-id:subject :from:to:content-type; b=jJ0RzXdm8jcRsv00jPI9S1VQoUxXNMWS3Se60+A8eK0vYONqVUj/H06sWY1bWLI/+f AJd6iDtwXJ5k1a7YDnRgoRd5BcAGziU1M/xZ3WVgr1s3of5ZFOpv6BTlMugPGdaZqz78 vlpvsV9c9GIwxsafaIXeAFRcTZyizI2IsKxBQ=
- Sender: subbarao2z2@gmail.com
There is a very accessible book-length introduction to Reinforcement Learning at
http://www.cs.ualberta.ca/~sutton/book/ebook/the-book.html
You might want to read Chapters 6 and 7 from that book (7, in particular, makes the connection between
Temporal difference learning and Montecarlo learning---and leads to TD(\lambda) class of approaches).
Rao