A hybrid agent architecture integrating desire, intention and reinforcement learning

Authors:
Ah-Hwee Tan;Yew-Soon Ong;Akejariyawong Tapanuj
Affiliations:
School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore;School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore;School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore
Venue:
Expert Systems with Applications: An International Journal
Year:
2011

Citing 22
Cited 3

A massively parallel architecture for a self-organizing neural pattern recognition machine

Computer Vision, Graphics, and Image Processing
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
The uses of plans

Artificial Intelligence
Adaptive resonance associative map

Neural Networks
Cambrian intelligence: the early history of the new AI

Cambrian intelligence: the early history of the new AI
Learning plans without a priori knowledge

Adaptive Behavior
Sequence Learning in the ACT-R Cognitive Architecture: Empirical Analysis of a Hybrid Model

Sequence Learning - Paradigms, Algorithms, and Applications
Embodied cognition: a field guide

Artificial Intelligence
Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)

Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)
Folk Psychology for Human Modelling: Extending the BDI Paradigm

AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 1
Predictive neural networks for gene expression data analysis

Neural Networks
Self-Organizing Cognitive Agents and Reinforcement Learning in Multi-Agent Environment

IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Plans as Products of Learning

IAT '06 Proceedings of the IEEE/WIC/ACM international conference on Intelligent Agent Technology
Intelligence Through Interaction: Towards a Unified Theory for Learning

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Direct code access in self-organizing neural networks for reinforcement learning

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Commitment and effectiveness of situated agents

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 1
A hybrid architecture combining reactive plan execution and reactive learning

PRICAI'06 Proceedings of the 9th Pacific Rim international conference on Artificial intelligence
Learning in BDI multi-agent systems

CLIMA IV'04 Proceedings of the 4th international conference on Computational Logic in Multi-Agent Systems
Learning plans with patterns of actions in bounded-rational agents

KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
Self-Organizing Neural Architectures and Cooperative Learning in a Multiagent Environment

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Integrating Temporal Difference Methods and Self-Organizing Neural Networks for Reinforcement Learning With Delayed Evaluative Feedback

IEEE Transactions on Neural Networks

Reinforcement learning approach to goal-regulation in a self-evolutionary manufacturing system

Expert Systems with Applications: An International Journal
Combining adaptive goal-driven agents with mixed multi-unit combinatorial auctions

Proceedings of the 13th International Conference on Computer Systems and Technologies
A reinforcement learning approach to improve the argument selection effectiveness in argumentation-based negotiation

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

This paper presents a hybrid agent architecture that integrates the behaviours of BDI agents, specifically desire and intention, with a neural network based reinforcement learner known as Temporal Difference-Fusion Architecture for Learning and COgNition (TD-FALCON). With the explicit maintenance of goals, the agent performs reinforcement learning with the awareness of its objectives instead of relying on external reinforcement signals. More importantly, the intention module equips the hybrid architecture with deliberative planning capabilities, enabling the agent to purposefully maintain an agenda of actions to perform and reducing the need of constantly sensing the environment. Through reinforcement learning, plans can also be learned and evaluated without the rigidity of user-defined plans as used in traditional BDI systems. For intention and reinforcement learning to work cooperatively, two strategies are presented for combining the intention module and the reactive learning module for decision making in a real time environment. Our case study based on a minefield navigation domain investigates how the desire and intention modules may cooperatively enhance the capability of a pure reinforcement learner. The empirical results show that the hybrid architecture is able to learn plans efficiently and tap both intentional and reactive action execution to yield a robust performance.