Multiagent reinforcement learning with adaptive state focus


Reference:
L. Busoniu, B. De Schutter, and R. Babuska, "Multiagent reinforcement learning with adaptive state focus," Proceedings of the 17th Belgium-Netherlands Conference on Artificial Intelligence (BNAIC 2005) (K. Verbeeck, K. Tuyls, A. Nowé, B. Manderick, and B. Kuijpers, eds.), Brussels, Belgium, pp. 35-42, Oct. 2005.

Abstract:
In realistic multiagent systems, learning on the basis of complete state information is not feasible. We introduce adaptive state focus Q-learning, a class of methods derived from Q-learning that start learning with only the state information that is strictly necessary for a single agent to perform the task, and that monitor the convergence of learning. If lack of convergence is detected, the learner dynamically expands its state space to incorporate more state information (e.g., states of other agents). Learning is faster and takes less resources than if the complete state were considered from the start, while being able to handle situations where agents interfere in pursuing their goals. We illustrate our approach by instantiating a simple version of such a method, and by showing that it outperforms learning with full state information without being hindered by the deficiencies of learning on the basis of a single agent's state.


Downloads:
 * Corresponding technical report: pdf file (188 KB)
      Note: More information on the pdf file format mentioned above can be found here.


Bibtex entry:

@inproceedings{BusDeS:05-017,
        author={L. Bu{\c{s}}oniu and B. {De Schutter} and R. Babu{\v{s}}ka},
        title={Multiagent reinforcement learning with adaptive state focus},
        booktitle={Proceedings of the 17th Belgium-Netherlands Conference on Artificial Intelligence (BNAIC 2005)},
        editor={K. Verbeeck and K. Tuyls and A. Now\'e and B. Manderick and B. Kuijpers},
        address={Brussels, Belgium},
        pages={35--42},
        month=oct,
        year={2005}
        }



Go to the publications overview page.


This page is maintained by Bart De Schutter. Last update: December 15, 2015.