Acquisition of hierarchical reactive skills in a unified cognitive architecture

Authors:
Pat Langley;Dongkyu Choi;Seth Rogers
Affiliations:
Computational Learning Laboratory, Center for the Study of Language and Information, Stanford University, Stanford, CA 94305, USA;Computational Learning Laboratory, Center for the Study of Language and Information, Stanford University, Stanford, CA 94305, USA;Computational Learning Laboratory, Center for the Study of Language and Information, Stanford University, Stanford, CA 94305, USA
Venue:
Cognitive Systems Research
Year:
2009

Citing 20
Cited 3

Quantitative results concerning the utility of explanation-based learning

Artificial Intelligence
Unified theories of cognition

Unified theories of cognition
A design for the ICARUS architecture

ACM SIGART Bulletin
Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization

Machine Learning - Special issue on case-based reasoning
Acquisition of Children's Addition Strategies: A Model of Impasse-Free, Knowledge-Level Learning

Machine Learning - Special issue on computational models of human learning
Learning to Take Actions

Machine Learning
Using background knowledge to speed reinforcement learning in physical agents

Proceedings of the fifth international conference on Autonomous agents
A Heuristic Approach to the Discovery of Macro-Operators

Machine Learning
Chunking in Soar: The Anatomy of a General Learning Mechanism

Machine Learning
Learning Context-Free Grammars with a Simplicity Bias

ECML '00 Proceedings of the 11th European Conference on Machine Learning
Learning Goal-Decomposition Rules using Exercises

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Many-Layered Learning

ICDL '02 Proceedings of the 2nd International Conference on Development and Learning
An Architecture for Persistent Reactive Behavior

AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 2
Learning hierarchical task networks by observation

ICML '06 Proceedings of the 23rd international conference on Machine learning
Learning Recursive Control Programs from Problem Solving

The Journal of Machine Learning Research
Teleo-reactive programs for agent control

Journal of Artificial Intelligence Research
Modeling cognitive development on the balance scale task

IJCAI'83 Proceedings of the Eighth international joint conference on Artificial intelligence - Volume 1
Acquiring recursive concepts with explanation-based learning

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
The effect of rule use on the utility of explanation-based learning

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
SteppingStone: an empirical and analytical evaluation

AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2

Knowledge-based control of a humanoid robot

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
PASAR: An integrated model of prediction, anticipation, sensation, attention and response for artificial sensorimotor systems

Information Sciences: an International Journal
Including cognitive biases and distance-based rewards in a connectionist model of complex problem solving

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we review Icarus, a cognitive architecture that utilizes hierarchical skills and concepts for reactive execution in physical environments. In addition, we present two extensions to the framework. The first involves the incorporation of means-ends analysis, which lets the system compose known skills to solve novel problems. The second involves the storage of new skills that are based on successful means-ends traces. We report experimental studies of these mechanisms on three distinct domains. Our results suggest that the two methods interact to acquire useful skill hierarchies that generalize well and that reduce the effort required to handle new tasks. We conclude with a discussion of related work on learning and prospects for additional research, including extending the framework to cover developmental phenomena.