Master Level Theses

Here you can find proposals for master thesis (20 CFU for each student)

Machine Learning

Title:	Reinforcement Learning in Poker
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.
Tutor:	Marcello Restelli (restelli-AT-elet-DOT-polimi-DOT-it)
Start:	Anytime
Number of students:	1-2
CFU:	20-40

Affective Computing

Title:	Affective VideoGames
Description:	The goal of this activity is to develop an interactive video game (Car game, Shoot them up, Strategic game ..) able to adapt its behaviour in order to maximize your enjoyment. The game will measure your excitement by analizing your biological signals, which mirror your emotional state. The system will be able to adjust some parameters (i.e difficulty of car game circuits, opponets strength ...) in order to keep you egnagemet constant: "In your flow zone!". Project phases: Design and implementation of the game (it is possible to start form avaliable open source game) Design of experimental protocol used to stimulate particolar emotions. Data acquisition by usign biological sensors during the playing experience. Off-line classification of data with avaliable tools. Desing and develop of on-line classifier sistem for emotion recognition Closed loop control: the game reacts to the user emotional state changing its behaviour. These projects allow to experiment with biological-data acquisition tools and videogames design. The project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)
Tutor:	Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start:	Anytime
Number of students:	1 to 3
CFU:	2.5 to 20

Title:	Affective recognition in multimedia contexts
Description:	The goal of this activity is to develop an interactive multimedia application (advertisement, e-learning, reccomenadation system) able to capture your emotional state (interests, excitement, anger, joy) while whatching to images, sounds etc. The application will measure your excitement by analizing your biological signals, which mirror your emotional state. The system could be used to give feedback on the quality of multimedia content (i.e goodness of the advertisement, enjoyment of the movie ...) Project phases: Design and implementation of the multimedia application. Design of experimental protocol used to stimulate particolar emotions. Data acquisition by usign biological sensors during the multimedia experience. Off-line classification of data with avaliable tools. Desing and develop of on-line classifier sistem for emotion recognition Closed loop control: the multimedia application will provide contents according to your enjoyment . These projects allow to experiment with biological-data acquisition tools and multimedia application design. The project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)
Tutor:	Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start:	Anytime
Number of students:	1 to 3
CFU:	2.5 to 20

Title:	Affective robotics
Description:	The goal of this activity is to develop an rehabilitation robotic game able to capture your emotional state (interests, excitement, anger, joy, stress) while intereacting with the robot. The application will measure your excitement by analizing your biological signals, which mirror your emotional state. The system could be used to adapt the therapy (executed by the game) according to the patien's needs. We believe the quality of the theraphy is related to the subject's emotional state. The long term goal is to keep the user into a specific emotional state in order to maximize the theraphy efficacy. Project phases: Design and implementation of the robotic game on the avaliable robot. Design of experimental protocol used to stimulate particolar emotions. Data acquisition by usign biological sensors during the interaction with the robot. Off-line classification of data with avaliable tools. Desing and develop of on-line classifier sistem for emotion recognition Closed loop control: the thrapy will be adapted to the patient's needs. These projects allow to experiment with biological-data acquisition tools, robots and videogame design. The project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)
Tutor:	Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start:	Anytime
Number of students:	1 to 3
CFU:	2.5 to 20

Title:	Driving companions
Description:	The goal of this activity is to develop an application that is able to capture your emotional state (stress, attention level .. ) while driving standard cars. The application will measure the driver's stress level by analizing his biological signals, which mirror the phisiological state, and could be used to give feedbacks to the driver in dangerous situations. Project phases: Design of experimental protocol used to stimulate particolar emotions. Data acquisition by usign biological sensors while driving in different conditions (city, highway, country ..) Off-line classification of data with avaliable tools. Desing and develop of on-line classifier sistem for emotion recognition Closed loop control: the car will give audio/visual feedbacks to the user letting him know its phisiological state These projects allow to experiment with biological-data acquisition tools, robots and videogame design. The project consists on the realization of one or more phases depending on the difficulty/cfu to be achieved and to the competences of the candidate(s)
Tutor:	Cristiano Alessandro (alessandro-AT-elet-DOT-polimi-DOT-it), Simone Tognetti (togetti-AT-elet-DOT-polimi-DOT-it)
Start:	Anytime
Number of students:	1 to 3
CFU:	2.5 to 20