Rule value reinforcement learning for cognitive agents

Authors:
Chris Child;Kostas Stathis
Affiliations:
City University, London, UK;City University, London, UK
Venue:
AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
Year:
2006

Citing 2
Cited 1

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
The apriori stochastic dependency detection (ASDD) algorithm for learning stochastic logic rules

CLIMA IV'04 Proceedings of the 4th international conference on Computational Logic in Multi-Agent Systems

Situating Cognitive Agents in GOLEM

Engineering Environment-Mediated Multi-Agent Systems

Quantified Score

Hi-index	0.00

Visualization

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.