Multi-agent reward analysis for learning in noisy domains

Explore this paper's citation graph

Summary

This paper presents a new reward evaluation method that provides a visualization of the tradeoff between coordination among the agents and the difficulty of the learning problem each agent faces, and shows that in the more difficult dynamic domain, this method provides a two order of magnitude speedup in selecting a good reward.

Type
article
Published
2005-07-25
Cited by
47
References
27
Access
Open access

Keywords

Computer science, Visualization, A priori and a posteriori, Domain (mathematical analysis), Property (philosophy)

References

Cited by

Related papers