AIRWiki

2008-09-29T14:18:58Z

MarcelloRestelli: /* Project Proposals (for courses, theses, ...) */

Welcome to AIRWiki!
AIRWiki is AIRLab's [http://en.wikipedia.org/wiki/Wiki wiki]. AIRLab is the '''Artificial Intelligence and Robotics Laboratory''' of the '''Politecnico di Milano''' University (Italy).

AIRWiki was born as a tool for teachers, researchers and students to share information about projects in an easy and quick way. However, it quickly evolved into a display of the activities of AIRLab too: you are invited to browse this wiki, to discover what we work on.

If you are looking for a description of what the AIRLab is, who works in it, and what scientific interests they have, the best place is the [http://www.airlab.elet.polimi.it/ AIRLab website]; but if you want an overview of what we are actually ''doing'', AIRWiki is the right place!

== Research areas ==
At the AIRLab we work on a very broad range of topics, organized in these areas:
* [[Agents, Multiagent Systems, Agencies]]
* [[BioSignal Analysis]]
* [[Computer Vision and Image Analysis]]
* [[E-Science]]
* [[Machine Learning]]
* [[Ontologies and Semantic Web]]
* [[Philosophy of Artificial Intelligence]]
* [[Robotics]]
* [[Soft Computing]]
These areas are described in detail on [http://www.airlab.elet.polimi.it/index.php/airlab/research_areas this page] of [http://www.airlab.elet.polimi.it/ AIRLab's website].

== Projects ==
Research work in the above areas is done within '''projects'''. Details about active and finished projects are available at the [[Projects]] page. Ongoing projects are covered as soon as enough - and structured enough - information about them is available.

Information about how to set up and manage a project page can be found at [[Projects - HOWTO]].

== Project Proposals (for courses, theses, ...) ==
Proposals of course or thesis projects for students are available at the following pages:

[[First Level Course Projects]]

[[First Level Theses]]

[[Master Level Course Projects]]

[[Master Level Theses]]

If you are interested in any proposal you can contact the tutors by email.

== How do I access the contents of this wiki? ==
AIRWiki is conceptually composed of two layers:
* a '''public layer''', readable by everyone on the internet and modifiable by AIRWiki's [[Registered users]];
* a '''private layer''', reserved to the [[Registered users]] (who can read and edit its contents).
More information about how such layers are actually implemented and how to access the private layer is available in the [[Layers]] page.

The public layer of AIRWiki is relatively stable: it is mainly constituted by documentation about past and ongoing projects, accessible through the [[Projects]] page. In addition to that, it includes useful information about the AIRLab (see [[#The AIRLab]]) and tutorials for AIRLab users (see [[#AIRLab survival guide]]).

The private layer is used by the people working on the projects as a repository of all the information related to them. Much of this information will eventually be suitably formatted and moved to the public layer.

== How can I contribute? ==
Contribution to the wiki (i.e. creation and modification of pages) is limited to [[Registered users]].

If you are a registered user and have information you want to share (description of what you do, links to useful sources of information, HOWTOs, and so on) just publish them on AIRWiki: it's easy and - dare we say it? - fun! As a guideline, consider putting on AIRWiki everything ''you'' would have liked to find there... instead of being forced to find out the hard way. And everything future students who will build upon your work would like to find.

At [[Projects - HOWTO]] you can find instructions and guidelines about how to set up a page for the project you work on and how to add new information to it.

Moreover, a wiki always needs help in terms of maintenance, linking between pages, shaping of a structure and so on. And well, in this very moment it also needs a logo ;-) If you want to help please send an email to either migliore (at) elet (dot) polimi (dot) it or eynard (at) elet (dot) polimi (dot) it.

== The AIRLab ==
Work (generally speaking) is done somewhere, using something and to reach some goal ;-) For the AIRLab, the following links tell you...
* ...where: [[The Labs]]
* ...using what: [[What's in the AIRLab]]
* ...why: [[Projects]]

If you want details about who the professors and researchers working at the AIRLab are and what scientific work they do, just go to the [http://www.airlab.elet.polimi.it/ AIRLab website].

== AIRLab survival guide ==
Some things are neither scientific nor technical, but you must know them all the same to work in the AIRLab...
* [[Bureaucracy]] (administrative procedures)
* [[Tips'n'tricks]] (things that can save you much trouble)
* [[AIRLab rules]] (they are few and simple, but you have to follow them)

As we are on the subject of survival (read: how to avoid hurting yourself or others), remember that '''to work in the AIRLab you must know the [[Safety norms]] and comply with them'''.

First Level Theses

2008-09-29T14:06:31Z

MarcelloRestelli:

==== Robotics ====
{{Project template
|title=Simulation of 6-DOF Robot Manipulator
|tutor=Marcello Restelli (restelli-AT-elet-DOT-polimi-DOT-it)
|description=The goal of this project is to develop a simulator for a 6-DOF robot manipulator, using the [http://www.ode.org/ ode] (open dynamics engine) library for simulating the rigid body dynamics. The project involves three different phases:
* Building the physical model of the manipulator
* Implementing the forward and inverse kinematic routines
* Implementing the trajectory planning routines
* Implementing the control modules
* Implementing an interface to control the robot movements

This project allows to put into practice what has been explained during the first part of the course of Robotics.

The project can be turned into a thesis, by using the simulated manipulator to perform some learning experiments.
|start=Anytime
|number=2-3
|cfu=10-15
|image=puma6dof1.jpg}}

2008-09-29T14:02:28Z

MarcelloRestelli:

Master Level Course Projects

2008-09-29T14:02:19Z

MarcelloRestelli:

Here you can find a list of project proposals for the courses of "Laboratorio di Intelligenza Artificiale e Robotica" and "Soft Computing"





==== Machine Learning ====

{{Project template
|title=Reinforcement Learning Competition
|tutor=Marcello Restelli (restelli-AT-elet-DOT-polimi-DOT-it)
|description=This project has the goal of participating to (and possibly winning ;)) the 2009 Reinforcement Learning competition. To have an idea of what participate to such a competition means you can have a look at the website of the [http://rl-competition.org/content/view/51/79/ 2008 RL competition].
The problems that will be proposed are still unknown. As soon as the domains will be published, the work will start by analyzing their main characteristics and, then we will identify which RL algorithms are most suited for solving such problems. After an implementation phase, the project will required a long experimental period to tune the parameters of the learning algorithms in order to improve the performance as much as possible.
|start=January, 2009
|number=2-4
|cfu=10-20
|image=keepaway.gif}}

File:Puma6dof1.jpg

2008-09-29T13:31:17Z

MarcelloRestelli:

First Level Course Projects

2008-09-29T13:30:35Z

MarcelloRestelli:

Master Level Theses

2008-09-29T13:05:05Z

MarcelloRestelli:

==== Machine Learning ====

{{Project template
|title=Reinforcement Learning in Poker
|tutor=Marcello Restelli
|description=In this years, Artificial Intelligence research has shifted its attention from fully observable environments such as Chess to more challenging partially observable ones such as Poker.

Up to this moment research in this kind of environments, which can be formalized as Partially Observable Stochastic Games, has been more from a game theoretic point of view, thus focusing on the pursue of optimality and equilibrium, with no attention to payoff maximization, which may be more interesting in many real-world contexts.

On the other hand Reinforcement Learning techniques demonstrated to be successful in solving both fully observable problems, single and multi-agent, and single-agent partially observable ones, while lacking application to the partially observable multi-agent framework.

This research aims at studying the solution of Partially Observable Stochastic Games, analyzing the possibility to combine the Opponent Modeling concept with the well proven Reinforcement Learning solution techniques to solve problems in this framework, adopting Poker as testbed.
|start=Anytime
|number=1-2
|cfu=20-40
|image=PokerPRLT.png}}

Master Level Theses

2008-09-29T13:04:55Z

MarcelloRestelli:

==== Machine Learning ====

{{Project template
|title=Reinforcement Learning in Poker
|tutor=Marcello Restelli
|description=In this years, Artificial Intelligence research has shifted its attention from fully observable environments such as Chess to more challenging partially observable ones such as Poker.

Up to this moment research in this kind of environments, which can be formalized as Partially Observable Stochastic Games, has been more from a game theoretic point of view, thus focusing on the pursue of optimality and equilibrium, with no attention to payoff maximization, which may be more interesting in many real-world contexts.

On the other hand Reinforcement Learning techniques demonstrated to be successful in solving both fully observable problems, single and multi-agent, and single-agent partially observable ones, while lacking application to the partially observable multi-agent framework.

This research aims at studying the solution of Partially Observable Stochastic Games, analyzing the possibility to combine the Opponent Modeling concept with the well proven Reinforcement Learning solution techniques to solve problems in this framework, adopting Poker as testbed.
|start=Anytime
|number=2
|cfu=20-40
|image=PokerPRLT.png}}

Master Level Course Projects

2008-09-29T11:30:11Z

MarcelloRestelli:

Here you can find a list of project proposals for the courses of "Laboratorio di Intelligenza Artificiale e Robotica" and "Soft Computing"





==== Machine Learning ====

{{Project template
|title=Reinforcement Learning in Poker
|tutor=Marcello Restelli
|description=In this years, Artificial Intelligence research has shifted its attention from fully observable environments such as Chess to more challenging partially observable ones such as Poker.

Up to this moment research in this kind of environments, which can be formalized as Partially Observable Stochastic Games, has been more from a game theoretic point of view, thus focusing on the pursue of optimality and equilibrium, with no attention to payoff maximization, which may be more interesting in many real-world contexts.

On the other hand Reinforcement Learning techniques demonstrated to be successful in solving both fully observable problems, single and multi-agent, and single-agent partially observable ones, while lacking application to the partially observable multi-agent framework.

This research aims at studying the solution of Partially Observable Stochastic Games, analyzing the possibility to combine the Opponent Modeling concept with the well proven Reinforcement Learning solution techniques to solve problems in this framework, adopting Poker as testbed.
|start=Anytime
|number=2
|cfu=5
|image=PokerPRLT.png}}

Master Level Theses

2008-09-29T11:29:57Z

MarcelloRestelli: New page:     ==== Machine Learni...

==== Machine Learning ====

{{Project template
|title=Reinforcement Learning in Poker
|tutor=Marcello Restelli
|description=In this years, Artificial Intelligence research has shifted its attention from fully observable environments such as Chess to more challenging partially observable ones such as Poker.

Up to this moment research in this kind of environments, which can be formalized as Partially Observable Stochastic Games, has been more from a game theoretic point of view, thus focusing on the pursue of optimality and equilibrium, with no attention to payoff maximization, which may be more interesting in many real-world contexts.

On the other hand Reinforcement Learning techniques demonstrated to be successful in solving both fully observable problems, single and multi-agent, and single-agent partially observable ones, while lacking application to the partially observable multi-agent framework.

This research aims at studying the solution of Partially Observable Stochastic Games, analyzing the possibility to combine the Opponent Modeling concept with the well proven Reinforcement Learning solution techniques to solve problems in this framework, adopting Poker as testbed.
|start=Anytime
|number=2
|cfu=5
|image=PokerPRLT.png}}

First Level Theses

2008-09-29T11:29:46Z

==== Machine Learning ====

{{Project template
|title=Reinforcement Learning in Poker
|tutor=Marcello Restelli
|description=In this years, Artificial Intelligence research has shifted its attention from fully observable environments such as Chess to more challenging partially observable ones such as Poker.

Up to this moment research in this kind of environments, which can be formalized as Partially Observable Stochastic Games, has been more from a game theoretic point of view, thus focusing on the pursue of optimality and equilibrium, with no attention to payoff maximization, which may be more interesting in many real-world contexts.

On the other hand Reinforcement Learning techniques demonstrated to be successful in solving both fully observable problems, single and multi-agent, and single-agent partially observable ones, while lacking application to the partially observable multi-agent framework.

This research aims at studying the solution of Partially Observable Stochastic Games, analyzing the possibility to combine the Opponent Modeling concept with the well proven Reinforcement Learning solution techniques to solve problems in this framework, adopting Poker as testbed.
|start=Anytime
|number=2
|cfu=5
|image=PokerPRLT.png}}

First Level Course Projects

2008-09-29T11:29:00Z

MarcelloRestelli:

First Level Course Projects

2008-09-29T11:28:43Z

MarcelloRestelli:

Master Level Course Projects

2008-09-29T11:27:51Z

MarcelloRestelli: New page: Here you can find a list of project proposals for the courses of "Laboratorio di Intelligenza Artificiale e Robotica" and "Soft Computing"

Here you can find a list of project proposals for the courses of "Laboratorio di Intelligenza Artificiale e Robotica" and "Soft Computing"

2008-09-29T11:22:46Z

MarcelloRestelli: New page: Here you can find a list of project proposals for the courses of "Progetto di Ingegneria Informatica" and "Progetto di Robotica"  <!--...

AIRWiki

2008-09-29T11:14:39Z

MarcelloRestelli: /* Project Proposals (for courses, theses, ...) */

Welcome to AIRWiki!
AIRWiki is AIRLab's [http://en.wikipedia.org/wiki/Wiki wiki]. AIRLab is the '''Artificial Intelligence and Robotics Laboratory''' of the '''Politecnico di Milano''' University (Italy).

AIRWiki was born as a tool for teachers, researchers and students to share information about projects in an easy and quick way. However, it quickly evolved into a display of the activities of AIRLab too: you are invited to browse this wiki, to discover what we work on.

If you are looking for a description of what the AIRLab is, who works in it, and what scientific interests they have, the best place is the [http://www.airlab.elet.polimi.it/ AIRLab website]; but if you want an overview of what we are actually ''doing'', AIRWiki is the right place!

== Research areas ==
At the AIRLab we work on a very broad range of topics, organized in these areas:
* [[Agents, Multiagent Systems, Agencies]]
* [[BioSignal Analysis]]
* [[Computer Vision and Image Analysis]]
* [[E-Science]]
* [[Machine Learning]]
* [[Ontologies and Semantic Web]]
* [[Philosophy of Artificial Intelligence]]
* [[Robotics]]
* [[Soft Computing]]
These areas are described in detail on [http://www.airlab.elet.polimi.it/index.php/airlab/research_areas this page] of [http://www.airlab.elet.polimi.it/ AIRLab's website].

== Projects ==
Research work in the above areas is done within '''projects'''. Details about active and finished projects are available at the [[Projects]] page. Ongoing projects are covered as soon as enough - and structured enough - information about them is available.

Information about how to set up and manage a project page can be found at [[Projects - HOWTO]].

== Project Proposals (for courses, theses, ...) ==
Proposals of course or thesis projects for students are available at the following pages:

[[First Level Course Projects]]

[[First Level Theses]]

[[Master Level Course Projects]]

[[Master Level Theses]]

== How do I access the contents of this wiki? ==
AIRWiki is conceptually composed of two layers:
* a '''public layer''', readable by everyone on the internet and modifiable by AIRWiki's [[Registered users]];
* a '''private layer''', reserved to the [[Registered users]] (who can read and edit its contents).
More information about how such layers are actually implemented and how to access the private layer is available in the [[Layers]] page.

The public layer of AIRWiki is relatively stable: it is mainly constituted by documentation about past and ongoing projects, accessible through the [[Projects]] page. In addition to that, it includes useful information about the AIRLab (see [[#The AIRLab]]) and tutorials for AIRLab users (see [[#AIRLab survival guide]]).

The private layer is used by the people working on the projects as a repository of all the information related to them. Much of this information will eventually be suitably formatted and moved to the public layer.

== How can I contribute? ==
Contribution to the wiki (i.e. creation and modification of pages) is limited to [[Registered users]].

If you are a registered user and have information you want to share (description of what you do, links to useful sources of information, HOWTOs, and so on) just publish them on AIRWiki: it's easy and - dare we say it? - fun! As a guideline, consider putting on AIRWiki everything ''you'' would have liked to find there... instead of being forced to find out the hard way. And everything future students who will build upon your work would like to find.

At [[Projects - HOWTO]] you can find instructions and guidelines about how to set up a page for the project you work on and how to add new information to it.

Moreover, a wiki always needs help in terms of maintenance, linking between pages, shaping of a structure and so on. And well, in this very moment it also needs a logo ;-) If you want to help please send an email to either migliore (at) elet (dot) polimi (dot) it or eynard (at) elet (dot) polimi (dot) it.

== The AIRLab ==
Work (generally speaking) is done somewhere, using something and to reach some goal ;-) For the AIRLab, the following links tell you...
* ...where: [[The Labs]]
* ...using what: [[What's in the AIRLab]]
* ...why: [[Projects]]

If you want details about who the professors and researchers working at the AIRLab are and what scientific work they do, just go to the [http://www.airlab.elet.polimi.it/ AIRLab website].

== AIRLab survival guide ==
Some things are neither scientific nor technical, but you must know them all the same to work in the AIRLab...
* [[Bureaucracy]] (administrative procedures)
* [[Tips'n'tricks]] (things that can save you much trouble)
* [[AIRLab rules]] (they are few and simple, but you have to follow them)

As we are on the subject of survival (read: how to avoid hurting yourself or others), remember that '''to work in the AIRLab you must know the [[Safety norms]] and comply with them'''.

Template:Project template

2008-09-29T11:05:37Z

MarcelloRestelli:

{| style="color:#333333;background-color:#eeeeff;" cellpadding="5" cellspacing="0"; frame="border"
!align="right" width="10%" |Title:
|width="50%"|{{{title}}}
|rowspan=6 width=40% | [[Image:{{{image}}}|center|300px]]
|-
!align="right" valign="top" |Description:
|{{{description}}}
|-
!align="right" |Tutor:
|{{{tutor}}}
|-
!align="right" |Start:
|{{{start|Anytime}}}
|-
!align="right" |Number of students:
|{{{number|1}}}
|-
!align="right" |CFU:
|{{{cfu|5}}}
|}

2008-09-29T10:44:48Z

MarcelloRestelli:

{| style="color:#333333;background-color:#eeeeff;" cellpadding="5" cellspacing="0"; frame="border"
!align="right" width="10%" |Title:
|width="50%"|{{{title}}}
|rowspan=5 width=40% | [[Image:{{{image}}}|40%]]
|-
!align="right" |Description:
|{{{description}}}
|-
!align="right" |Tutor:
|{{{tutor}}}
|-
!align="right" |Start:
|{{{start|Anytime}}}
|-
!align="right" |Number of students:
|{{{number|1}}}
|}