Ranking Functions in Large State Spaces - Artificial Intelligence Applications and Innovations - Part II Access content directly
Conference Papers Year : 2011

Ranking Functions in Large State Spaces

Klaus Häming
  • Function : Author
  • PersonId : 1014209
Gabriele Peters
  • Function : Author
  • PersonId : 1014210


Large state spaces pose a serious problem in many learning applications. This paper discusses a number of issues that arise when ranking functions are applied to such a domain. Since these functions, in their original introduction, need to store every possible world model, it seems obvious that they are applicable to small toy problems only. To disprove this we address a number of these issues and furthermore describe an application that indeed has a large state space. It is shown that an agent is enabled to learn in this environment by representing its belief state with a ranking function. This is achieved by introducing a new entailment operator that accounts for similarities in the state description.
Fichier principal
Vignette du fichier
978-3-642-23960-1_27_Chapter.pdf (353.08 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01571476 , version 1 (02-08-2017)





Klaus Häming, Gabriele Peters. Ranking Functions in Large State Spaces. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. pp.219-228, ⟨10.1007/978-3-642-23960-1_27⟩. ⟨hal-01571476⟩
56 View
58 Download



Gmail Facebook X LinkedIn More