Difference between revisions of "Multiobjective Reinforcement Learning Algorithms Elevator Group Control"
From AIRWiki
SimoneParisi (Talk | contribs) |
SimoneParisi (Talk | contribs) |
||
| Line 6: | Line 6: | ||
| resarea=Machine Learning | | resarea=Machine Learning | ||
| restopic=Multiobjective Optimization | | restopic=Multiobjective Optimization | ||
| − | | start= | + | | start=16/04/2013 |
| + | | end= | ||
| level=Ms | | level=Ms | ||
| type=Thesis | | type=Thesis | ||
Latest revision as of 23:59, 23 April 2013
Multiobjective Reinforcement Learning Algorithms Elevator Group Control
| |
| Short Description: | The goal of the project is to study MO RL algorithms and to apply them on an intelligent system for elevator group control. |
| Coordinator: | MarcelloRestelli (restelli@elet.polimi.it) |
| Tutor: | MarcelloRestelli (restelli@elet.polimi.it) |
| Collaborator: | |
| Students: | SimoneParisi (simone.parisi@polimi.it), NicolaSmacchia (nicola.smacchia@polimi.it) |
| Research Area: | Machine Learning |
| Research Topic: | Multiobjective Optimization |
| Start: | 16/04/2013 |
| Status: | Active |
| Level: | Ms |
| Type: | Thesis |
Dopo uno studio dello stato dell'arte si analizzeranno nuovi possibili algoritmi RL per problemi MO e si testeranno sul problema di controllo di un gruppo di ascensori.
