Advanced

Learning and Planning of Situated Resource Bounded Agents

Nowaczyk, Slawomir LU (2006) 23rd Annual Workshop of the Swedish Artificial Intelligence Society In Proceedings of the 23rd Annual Workshop of the Swedish Artificial Intelligence Society
Abstract
This paper presents an investigation of rational agents that have limited computational resources and that can interact with their environments. We

analyse how such agents can combine deductive reasoning using domain knowledge and inductive learning from past experiences, while remaining time-aware in a manner appropriate for beings situated in a dynamic universe.

In particular, we consider how they can create and reason about partial plans, choose and execute the best ones of them — in such way as to acquire the most knowledge. We also discuss what are the different types of interactions with the world and how they can influence agent’s ability to consciously direct its own learning process.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Proceedings of the 23rd Annual Workshop of the Swedish Artificial Intelligence Society
conference name
23rd Annual Workshop of the Swedish Artificial Intelligence Society
ISSN
0348-0542
language
English
LU publication?
yes
id
4a69de92-0370-49a0-b8ac-5b44a2c35beb (old id 1002959)
date added to LUP
2008-02-01 13:49:25
date last changed
2016-04-16 06:21:45
@inproceedings{4a69de92-0370-49a0-b8ac-5b44a2c35beb,
  abstract     = {This paper presents an investigation of rational agents that have limited computational resources and that can interact with their environments. We<br/><br>
analyse how such agents can combine deductive reasoning using domain knowledge and inductive learning from past experiences, while remaining time-aware in a manner appropriate for beings situated in a dynamic universe.<br/><br>
In particular, we consider how they can create and reason about partial plans, choose and execute the best ones of them — in such way as to acquire the most knowledge. We also discuss what are the different types of interactions with the world and how they can influence agent’s ability to consciously direct its own learning process.},
  author       = {Nowaczyk, Slawomir},
  booktitle    = {Proceedings of the 23rd Annual Workshop of the Swedish Artificial Intelligence Society},
  issn         = {0348-0542},
  language     = {eng},
  title        = {Learning and Planning of Situated Resource Bounded Agents},
  year         = {2006},
}