Rule Value Reinforcement Learning for Cognitive Agents

Child, C. H. T. & Stathis, K. (2006). Rule Value Reinforcement Learning for Cognitive Agents. Paper presented at the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS`06), 8 - 12 May 2006, Hakodate, Hokkaido, Japan.

[img]
Preview
PDF
Download (223kB) | Preview

Abstract

RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule representation. The algorithm attaches values to learned rules by adapting reinforcement learning. Structure captured by the rules is used to form a policy. The resulting rule values represent the utility of taking an action if the rule`s conditions are present in the agent`s current percept. Advantages of the new framework are demonstrated, through examples in a predator-prey environment.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: School of Informatics > Department of Computing
URI: http://openaccess.city.ac.uk/id/eprint/3001

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics