City Research Online

Rule Value Reinforcement Learning for Cognitive Agents

Child, C. H. T. and 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.

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.

Publication Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
URI: http://openaccess.city.ac.uk/id/eprint/3001
[img]
Preview
PDF
Download (223kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login