Sciweavers

448 search results - page 8 / 90
» Abstraction in Predictive State Representations
Sort
View
ATAL
2010
Springer
14 years 11 months ago
Learning multi-agent state space representations
This paper describes an algorithm, called CQ-learning, which learns to adapt the state representation for multi-agent systems in order to coordinate with other agents. We propose ...
Yann-Michaël De Hauwere, Peter Vrancx, Ann No...
ECAI
2000
Springer
15 years 2 months ago
Iterated Revision by Epistemic States: Axioms, Semantics and Syntax
Abstract. We propose a very general syntactical notion of epistemic state and a compact axiomatization for iterated revision when the new information is an epistemic state. We set ...
Salem Benferhat, Sébastien Konieczny, Odile...
MAGS
2007
168views more  MAGS 2007»
14 years 9 months ago
Agent-based protein structure prediction
A protein is identified by a finite sequence of amino acids, each of them chosen from a set of 20 elements. The Protein Structure Prediction Problem is the problem of predicting...
Luca Bortolussi, Agostino Dovier, Federico Fogolar...
CORR
2010
Springer
204views Education» more  CORR 2010»
14 years 8 months ago
Predictive State Temporal Difference Learning
We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications...
Byron Boots, Geoffrey J. Gordon
ISCIS
2009
Springer
15 years 4 months ago
Predicting future object states using learned affordances
Abstract—The notion of affordances was proposed by J.J. Gibson, to refer to the action possibilities offered to the organism by its environment. In a previous formalization, affo...
Emre Ugur, Erol Sahin, Erhan Oztop