Adaptive Multi-Agent Programming in GTGolog

Authors:
Alberto Finzi;Thomas Lukasiewicz
Affiliations:
Inst. für Informationssysteme, TU Wien, Favoritenstr. 9-11, A-1040 Wien and DIS, Università di Roma “La Sapienza”, Via Salaria 113, I-00198 Roma;DIS, Università di Roma “La Sapienza”, Via Salaria 113, I-00198 Roma and Inst. für Informationssysteme, TU Wien, Favoritenstr. 9-11, A-1040 Wien
Venue:
Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Year:
2006

Citing 7
Cited 0

Knowlege in action: logical foundations for specifying and implementing dynamical systems

Knowlege in action: logical foundations for specifying and implementing dynamical systems
The MAXQ Method for Hierarchical Reinforcement Learning

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Decision-Theoretic, High-Level Agent Programming in the Situation Calculus

Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
State abstraction for programmable reinforcement learning agents

Eighteenth national conference on Artificial intelligence
Exploiting first-order regression in inductive policy selection

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Symbolic dynamic programming for first-order MDPs

IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Concurrent hierarchical reinforcement learning

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel approach to adaptive multi-agent programming, which is based on an integration of the agent programming language GTGolog with adaptive dynamic programming techniques. GTGolog combines explicit agent programming in Golog with game-theoretic multi-agent planning in stochastic games. In GTGolog, the transition probabilities and reward values of the domain must be provided with the model. The adaptive generalization of GTGolog proposed here is directed towards letting the agents themselves explore and adapt these data. We use high-level programs for the generation of both abstract states and optimal policies.