Hi there, welcome to Brian Tanner's research homepage. I just moved my page here from http://brian.tannerpages.com (a Joomla site on my own webserver). I think using Google Sites is a win.
You can reach me at: brian@tannerpages.com
Me
I'm currently a Ph.D student at the University of Alberta, studying reinforcement learning and artificial intelligence with
Professor Richard Sutton. I live in Edmonton with my wife Ariel, my son Lincoln (Link), and my two dogs Scooter and Trinity.
Interests
My
research interests have always been in AI, specifically in creating
intelligent systems that can learn and improve their performance with
minimal human interference. I want the agent to learn things for
itself, and I don't mind if it takes longer. I
co-chaired a workshop at NIPS 2006 on this topic.
An important step on this path is to figure out how we can fairly
evaluate AI algorithms so that we know what methods to prefer. This
has lead to an interest in empirical evaluation of reinforcement
learning algorithms. I was the technical committee chair for the
2008 RL-Competition, and am currently working on a large system for evaluating RL algorithms, the
RL-Logbook..
I've also been busy with various open source projects like
RL-Glue,
RL-Viz, and the
RL-Library.
You could say that I'm a big believer in improving the field by
empowering the community with tools and projects that hopefully make
their life easier.
Before my Ph.D, I did a Masters in Alberta,
also with Rich, on
Temporal-Difference Networks. Before that, I got
an Honours Bachelor of Science from the University of Manitoba, where I
worked with
Dr. John Anderson.
My CV can be downloaded from Google base
here.
Recent Blog Posts
Research Thoughts
Research Thoughts
-
Thoughts about the role of authors and reviewers in academic research
John Langford had an interesting post (as usual) on his Hunch.net blog about Adversarial Research. In the comment to his post, someone anonymously posted the following:I believe you ...
Posted Jan 29, 2009, 7:12 PM by Brian Tanner
-
Radical Transparency in Research
I've been stewing on some topics for a long time. I'm a real zealot for strong experimental design and rigorous empiricism when evaluating my work and the work ...
Posted Aug 6, 2008, 2:33 PM by Brian Tanner
Good Samaratin
Workshops and Events I've Helped Organize
2008 :: Reinforcement Learning Competition Workshop
Co-Chair with Shimon Whiteson and Adam White
Helsinki, Finland, International Conference on Machine Learning
http://rl-competition.org/content/view/49/75/
2008 :: Barbados Reinforcement Learning Workshop
Co-Organized Sessions / Logistics
Holetown, Barbados
http://groups.google.com/group/rl-list/web/barbados-reinforcement-learning-workshop-2008
2007 - 2008 :: Reinforcement Learning Competition
Technical Commitee Chair
http://rl-competition.org
2006 :: Grounding Perception, Knowledge, and Cognition in Sensori-Motor Experience
Co-Chair with Michael James and David Wingate
Whistler, Canada, Advances in Neural Information Programming Systems (NIPS)
http://prw06.rl-community.org/
Open Source Software Projects
Here are some software projects I'm involved in. If you're interested in helping out or learning more, please contact me!
RL-Glue
http://glue.rl-community.org
http://rl-glue.googlecode.com
Contributor
Click
here to see a video of a talk I gave at the Machine Learning Open Source Software workshop at NIPS in 2008.
RL-Glue Extensions (Codecs)
http://rl-glue-ext.googlecode.com
Contributor
RL-Library
http://rl-library.googlecode.com
Contributor
RL-Competition
http://rl-competition.googlecode.com
2008 Technical Commitee Chair
RL-Viz
http://rl-viz.googlecode.com
Lead Developer/Designer
RL-RecordBook
http://logbook.rl-community.org
Lead Developer/Designer
BT RL Agent Library
http://bt-agentlib.googlecode.com
Lead Developer/Designer
TD Networks
http://td-networks.googlecode.com
Lead Developer/Designer
Amazon Web Service Remote Signing
http://aws-remote-signing.googlecode.com
Lead Developer/Designer
My Family