The amount of digitally available but heterogeneous information about the world is remarkable, and new technologies such as self-driving cars, smart homes or the "internet of things" will further increase it. In this paper we examine certain aspects of the problem of how such heterogeneous information can be harnessed by intelligent agents. We first discuss potentials and limitations of some existing approaches, followed by two investigations. The focus of the first investigation is on using the novel experimentation platform {\em Malmo} to obtain a better understanding of the problem. The focus of the second investigation is on understanding how information about the hardware of different agents (such as self-driving cars), the agents' sensory data, and physical or causal information can be utilized for knowledge transfer between agents and subsequent more data-efficient decision making. Finally, we present some thoughts on what a general theory for the problem could look like, and formulate open questions.
from cs.AI updates on arXiv.org http://ift.tt/1VYei2h
via IFTTT
No comments:
Post a Comment