Binary Space Partitioning as Intrinsic Reward (Skaba)

Added by Deon Garrett over 5 years ago

An autonomous agent embodied in a humanoid robot, in order to learn from the overwhelming flow of raw and noisy sensory, has to effectively reduce the high spatial-temporal data dimensionality. In this paper we propose a novel method of unsupervised feature extraction and selection with binary space partitioning, followed by a computation of information gain that is interpreted as intrinsic reward, then applied as immediate-reward signal for the reinforcement-learning. The space partitioning is executed by tiny codelets running on a simulated Turing Machine. The features are represented by concept nodes arranged in a hierarchy, in which those of a lower level become the input vectors of a higher level.

paper_43.pdf (195.8 kB)


Replies (1)

RE: Binary Space Partitioning as Intrinsic Reward (Skaba) - Added by Victoria William 4 months ago

What is the best dividing write for my PC?

Is it FAT32 or NSTF? I need to amplify on the capacity limit. <a href="http://www.assignmentmoz.co.uk/">assignment help service At Assignment Moz</a> I’m as yet 20GB down on the bigger hard drive of 300GB limit. Is it best to utilize XP or Vista? In the event that anybody out there can help I would be extremely thankful.

(1-1/1)