LEARNING  IN  AGENTS  AND

MULTI-AGENT  SYSTEMS




 (2011/12)

 

(Aprenentatge en agents i sistemes multiagent)

 

 

Course in the Ph.D. Program in Artificial Intelligence and the Master in Artificial Intelligence at the LSI Dept. at the UPC

 

Advisors | Syllabus and Course Slides | List of proposed projects | Bibliography | Links

Advisors

Ulises Cortés (UC)
(Campus Nord, K2M-121, )

Mario Martin (MM)
(Campus Nord, K2M-121, )

Syllabus and Course Slides

Part I. Behavior Learning  (MM)

        1. Topics in Behavior Learning

            2. Reinforcement Learning

                        2.1  RL Framework (print version)

                        2.2  Goal Definition (print version)

            3. Searching for optimal policies  (print version)

                        3.1  Value functions and Optimal Policies  

                        3.2  Dynamic Programming

                                   3.2.1  Policy iteration

                                   3.2.2  Value iteration

                                   3.2.3  Asynchronous versions

                        3.3  Reinforcement Learning algorithms (print version)

                                   3.3.1  Monte Carlo

                                   3.3.2  Q-learning

                                   3.3.3  Sarsa

                                   3.3.4  TD(lambda)

                                   3.3.5  Q(lambda)

            4.  Introduction to Game Theory (print version)


            5.  Learning to cooperate in MAS (print version)


            6. Patially Observable Markov Decision Problems (print version)


            7.  Generalization in RL (print version)

 

Part II  (UC)

Here
 

List of proposed projects

 

Bibliography

Part I. 

1.     Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA, 1998 (text, code and additonial material at  http://www.cs.ualberta.ca/~sutton/book/the-book.html).

2.     Dimitri P. Bertsekas and John Tsitsiklis. Neuro-Dynamic Programming. Athena Scientific , 1996. http://www.athenasc.com/ndpbook.html

 

Part II.

Here

Links

Some links to repositories, researchers and research groups related to the course

Part I.

1.     Repositories

Reinforcement Learning Warehouse

Reinforcement Learning Repository

Richard Sutton RL web page

2.     Conferences

NIPS 2003 Conference

International Conference on Machine Learning

EUROPEAN WORKSHOPS ON REINFORCEMENT LEARNING

IEEE TSMC: Special Issue on Learning Autonomous Robots

ML95 Workshop: Value Function Approximation in RL

ML94 Robot Learning

3.     Researchers and Research groups

Reinforcement Learning Group at the CMU

CMU Learning Lab

 

Richard Sutton web page

Andrew G. Barto's Home Page

Andrew W. Moore's Home Page

Singh's Reinforcement Learning Archive (papers)

Leslie Pack Kaelbling

 

Part II.

Here