Date: 2014-02-24
Hypotheses: This is a run for the record
Variation of: 20140208-NOOR
4 agents; 5 runs; 350 games
Experimental setting: This is a largely new different setting from the previous experiment [20140208-NOOR] F-measure uses Semantic precision and recall instead of syntactic. The matrix is symmetrics (the findings of one agent are communicated to the other one). Results with this setting have several constraints. The number of agents is 4, because with three agents in this setting they simply empty the correspondences (this is due to the structure of the network). As a consequence, the number of iterations for converging seems to be 350 (rougthly). It is not possible to compute the curve of incoherence (conjecture: Alcomo has memory leaks).
Class used: NOOEnvironment, AlignmentAdjustingAgent, AlignmentRevisionExperiment, ActionLogger, AverageLogger, Monitor.
Execution environment: MacBook Pro 15, C2D 2.66GHz, 8GB - MacOS X 6.8 - Java 1.6.0 HotSpot
This file can be retrieved from URL https://sake.re/20140224-NOOR
It is possible to check out the repository by cloning https://felapton.inrialpes.fr/cakes/20140224-NOOR.git
This experiment has been transferred from its initial location at https://gforge.inria.fr (not available any more)
See original markdown (20140224-NOOR.md) or HTML (20140224-NOOR.html) files.