servicerobotik.hs-weingarten.de
ZAFH - Autonome Mobile Serviceroboter
http://servicerobotik.hs-weingarten.de/en/teachingbox.php
Collaborative Center for Applied Research. The robot explores its environment by performing actions and receiving reward which may be delayed or missing for many time steps. Based on the reward, the robot continually improves its policy. Manual programming of policies in Java is also possible. Learning algorithms for supervised learning and reinforcement learning are provided in a Java library. Join our mailing list. In order to send comments, to obtain support or to hear when new releases are available.
amser.hs-weingarten.de
ZAFH - Autonome Mobile Serviceroboter
http://amser.hs-weingarten.de/en/teachingbox.php
Collaborative Center for Applied Research. The robot explores its environment by performing actions and receiving reward which may be delayed or missing for many time steps. Based on the reward, the robot continually improves its policy. Manual programming of policies in Java is also possible. Learning algorithms for supervised learning and reinforcement learning are provided in a Java library. Join our mailing list. In order to send comments, to obtain support or to hear when new releases are available.
amser.hs-weingarten.de
ZAFH - Autonome Mobile Serviceroboter
http://amser.hs-weingarten.de/en/teachingbox.php?exp=
Collaborative Center for Applied Research. The robot explores its environment by performing actions and receiving reward which may be delayed or missing for many time steps. Based on the reward, the robot continually improves its policy. Manual programming of policies in Java is also possible. Learning algorithms for supervised learning and reinforcement learning are provided in a Java library. Join our mailing list. In order to send comments, to obtain support or to hear when new releases are available.
sgez.blogspot.com
Trying to outrun my shadow since 2007: October 2011
http://sgez.blogspot.com/2011_10_01_archive.html
Trying to outrun my shadow since 2007. I am not a robot. I am a unicorn.". Saturday, October 22, 2011. Fedora 15 - my must have apps. First of sudo a yum update. Aptana Studio (download from www.aptana.com. RL-GLUE ( glue.rl-community.org/wiki/Main Page. Rl-glue python codec, pyro, pybrain, pygame, matplotlib, scipy, numpy, pybox2d, python-tools. LibreOffice ( Writer, Calc, Presentation. EasyLife ( www.easylifeproject.org/. Nvidia propriatory driver did not work on my old eFoce Go 7400. The safest way is:.
sgez.blogspot.com
Trying to outrun my shadow since 2007: Fedora 15 - my must have apps
http://sgez.blogspot.com/2011/10/fedora-15-my-must-have-apps.html
Trying to outrun my shadow since 2007. I am not a robot. I am a unicorn.". Saturday, October 22, 2011. Fedora 15 - my must have apps. First of sudo a yum update. Aptana Studio (download from www.aptana.com. RL-GLUE ( glue.rl-community.org/wiki/Main Page. Rl-glue python codec, pyro, pybrain, pygame, matplotlib, scipy, numpy, pybox2d, python-tools. LibreOffice ( Writer, Calc, Presentation. EasyLife ( www.easylifeproject.org/. Nvidia propriatory driver did not work on my old eFoce Go 7400.
general-game-playing.de
Links - General Game Playing
http://www.general-game-playing.de/links.html
Related Projects at TU-Dresden. Subscribe to the GGP mailing list. A low volume list with information about the competitions. You will also get help there if you want to develop your own general game player. The Stanford General Game Playing Website. Provides information about the Game Description Language (GDL), the GGP competitions and has some reference players for download. Website by Reykjavik University about CADIAPlayer. Publications by David Kaiser. About General Game Playing. RL-GGP was develope...
bradknox.net
Projects | W Bradley Knox, PhD
http://www.bradknox.net/projects
W Bradley Knox, PhD. Train a TAMER agent. Learning Social Interaction from the Wizard, 2012-. 2014 AAAI MLIS workshop. Learning from Human-Generated Reward, 2007-. Relevant publications: my dissertation and those in sub-projects below. Sub-projects on human-generated reward:. The TAMER framework is our myopic, model-based approach to learning only from human reward (described further here. Relevant publications: ICDL 2008, K-CAP 2009, HRI Late-breaking Reports 2012, ICSR 2013. 8211; In this line of resea...