Difference between revisions of "Project Proposals"

From AIRWiki
Jump to: navigation, search
(Machine Learning)
Line 16: Line 16:
 
|title=Reinforcement Learning in Poker
 
|title=Reinforcement Learning in Poker
 
|tutor=Marcello Restelli
 
|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.
 
|image=PokerPRLT.png}}
 
|image=PokerPRLT.png}}
  

Revision as of 11:48, 29 September 2008

Here are some proposals for different purposes


First level

Course Projects

Agents, Multiagent Systems, Agencies

BioSignal Analysis

Computer Vision and Image Analysis

E-Science

Machine Learning


Title: Reinforcement Learning in Poker
PokerPRLT.png
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
Start: Anytime
Number of students: 1
CFU: 5


Ontologies and Semantic Web

Philosophy of Artificial Intelligence

Robotics

Soft Computing

Theses

Agents, Multiagent Systems, Agencies

BioSignal Analysis

Computer Vision and Image Analysis

E-Science

Machine Learning


Title: Reinforcement Learning in Poker [[Image:{{{image}}}|center|300px]]
Description: {{{description}}}
Tutor: Marcello Restelli
Start: Anytime
Number of students: 1
CFU: 5


Ontologies and Semantic Web

Philosophy of Artificial Intelligence

Robotics

Soft Computing

Master Level

Course projects

Agents, Multiagent Systems, Agencies

BioSignal Analysis

Computer Vision and Image Analysis

E-Science

Machine Learning


Title: Reinforcement Learning in Poker [[Image:{{{image}}}|center|300px]]
Description: {{{description}}}
Tutor: Marcello Restelli
Start: Anytime
Number of students: 1
CFU: 5


Ontologies and Semantic Web

Philosophy of Artificial Intelligence

Robotics

Soft Computing

Theses

Agents, Multiagent Systems, Agencies

BioSignal Analysis

Computer Vision and Image Analysis

E-Science

Machine Learning


Title: Reinforcement Learning in Poker [[Image:{{{image}}}|center|300px]]
Description: {{{description}}}
Tutor: Marcello Restelli
Start: Anytime
Number of students: 1
CFU: 5


Ontologies and Semantic Web

Philosophy of Artificial Intelligence

Robotics

Soft Computing