EWRL2 (1995)


Artificial Intelligence and Robotics Project (PM-AI&R Project)
Dipartimento di Elettronica e Informazione
Politecnico di Milano
via Ponzio 34/5,
20133 Milano,

Conference Information

  • Announcement
  • Preliminary Program
  • Organizing and Program Committee
  • List of Participants with emails
  • List of Hotels
  • Intention Form

    Some links …

  • A tour of Politecnico di Milano (in Italian)
  • General information on Milano
  • A map of Milano
  • A map of Milano’s underground
  • Milano’s underground instructions for use


    Reinforcement learning (RL) is a growing research area within the machine learning community. To try to build an european community of people working in reinforcement learning, and to give visibility to the current situation in the old continent, we have decided to organize EWRL-2, the Second European Workshop on Reinforcement Learning. (EWRL-1, the First European Workshop on Reinforcement Learning, took place last September in Brussels.)

    The two-day workshop will be organized as follows. The first morning will be opened by a plenary talk given by Leslie Kaelbling.

    The rest of the workshop will be dedicated to presentations given by selected workshop participants. The length of presentations will be decided after we have some feedback on the number of participants.

    The workshop will be restricted to researchers active in the field and to their students.

    An inscription fee of Lire 200.000 (roughly $120 at current change) will cover local organization expenses and a social dinner on monday evening.

    Please communicate ASAP your intention to participate by means of the intention form below (e-mail is preferred: mdorigo@ulb.ac.be).
    Otherwise send intention forms to: Marco Dorigo, IRIDIA, Université Libre de Bruxelles, Avenue Franklin Roosvelt 50, CP 194/6, 1050 Bruxelles, Belgium.



    Preliminary Program

    Monday 18 September 1995


  • 09:00 – Introductory remarks 
  • 09:15 – Reinforcement Learning: The Good, The Bad, and The Ugly
    Leslie Kaelbling, Brown University, RI, USA. (Get a copy of the talk slides in regular form (one slide per page) or thumbnail form (four slides per page).) 
  • 10:15 – Coffee break 
  • 10:45 – Robot shaping and Behavior Engineering
    Marco ColombettiPM AI&R, Politecnico di Milano, Italy. (Get information about papers related to this talk.) 
  • 11:45 – Ant colonies and reinforcement learning for combinatorial optimization
    Marco DorigoIRIDIA, Université Libre de Bruxelles, Belgium. (Get a copy of the talk slides in regular form (one slide per page) or thumbnail form (four slides per page), or get a paper related to this talk.) 
  • 12:30 – Free time for lunch
    (Lunch is up to the attendees. A list of restaurants and cafeterias in the neighborhood will be provided.) 
  • 14:00 – Reinforcement learning, optimal control and neural control: How do they meet
    Hugues Bersini, IRIDIA, Université Libre de Bruxelles, Belgium. 
  • 14:45 – EIRA: Environment-independent reinforcement acceleration
    Juergen SchmidhuberIDSIA, Lugano, Switzerland. (Get a paper related to this talk.) 
  • 15:30 – Coffee break 
  • 16:00 – Training Q-agents
    Vincenzo Caironi, PM AI&R, Politecnico di Milano, Italy. (Get a copy of the talk slides, or get a IJ.14-IJIS97.ps.gz (280K) related to this talk.) 
  • 16:45 – Coffee break 
  • 17:15 – A Reinforcement Learning Scheme for Adaptive Link Allocation in ATM Networks
    Jakob Carlström, University of Uppsala, Sweden. (Get a copy of the talk slides.) 
  • 20:30 – Social dinner (organized by EWRL-2) 


  • Tuesday 20 September 1995

  • 09:00 – The influence of non Markovian environments on reinforcement learning
    Ann Nowè, Vrije Universiteit Brussel, Belgium. 
  • 09:45 – Fuzzy Classifier Systems and Fuzzy Q-Learning
    Andrea BonariniPM AI&R, Politecnico di Milano, Italy. (Get a copy of the talk slides.) 
  • 10:30 – Coffee break 
  • 11:00 – Fuzzy Q-Learning
    Pierre Yves Glorennec, INSA de Rennes, France. 
  • 11:45 – A Psychogenetic approach to learning sequences of actions
    Vittorio Maniezzo, Universitá di Bologna, Italy. 
  • 12:30 – Free time for lunch
    (Lunch is up to the attendees. A list of restaurants and cafeterias in the neighborhood will be provided.) 
  • 14:00 – Using Bayesian Estimators in Reinforcement Learning
    Jeremy Wyatt, University of Edinburgh, United Kingdom. (Get a copy of the talk slides.) 
  • 14:45 – Exploration versus Exploitation: simulation results
    Nicolas Meuleau, CEMAGREF, Antony, France. 
  • 15:30 – Coffee break 
  • 16:00 – Indirect Adaptive Exploration in Entropy Based Reinforcement Learning
    Ping Zhang, Université de Technologie de Compiegne, France. 
  • 16:30 – Reinforcement Learning by Construction of Hypothetical Targets
    Lars Asplund, University of Uppsala, Sweden. (Get a copy of the talk slides.) 
  • 17:00 – Teaching by means of Reinforcement
    Roberto Piola, Universitá di Torino, Italy. 
  • 17:30 – Final discussion 


    Organizing and Program Committee

    Hugues Bersini: IRIDIAULB, Brussels

    Andrea BonariniMarco ColombettiDipartimento di Elettronica e InformazionePolitecnico di Milano

    Marco DorigoIRIDIAULB, Brussels & Dipartimento di Elettronica e InformazionePolitecnico di Milano



    List of Participants with emails


  • Asplund Lars, University of Uppsala, Sweden, asplund@docs.uu.se
  • Bersini Hugues, IRIDIA, Université Libre de Bruxelles, Belgium, bersini@ulb.ac.be
  • Bonarini AndreaPM AI&R, Politecnico di Milano, Italy, bonarini@elet.polimi.it
  • Caironi Vincenzo, PM AI&R, Politecnico di Milano, Italy, caironi@elet.polimi.it
  • Carlström Jakob, University of Uppsala, Sweden, jakobc@docs.uu.se
  • Colombetti MarcoPM AI&R, Politecnico di Milano, Italy, colombet@elet.polimi.it
  • Dorigo MarcoIRIDIA, Université Libre de Bruxelles, Belgium, mdorigo@ulb.ac.be
  • Gambardella LucaIDSIA, Lugano, Switzerland, luca@idsia.ch
  • Glorennec Pierre Yves, INSA de Rennes, France, Pierre-Yves.Glorennec@irisa.fr
  • Kaelbling Leslie, Brown University, RI, USA, lpk@cs.brown.edu
  • Maniezzo Vittorio, Universitá di Bologna, Italy, maniezzo@elet.polimi.it
  • Marco WieringIDSIA, Lugano, Switzerland, marco@idsia.ch
  • Meuleau Nicolas, CEMAGREF, Antony, France, Nicolas.Meuleau@cemagref.fr
  • Munos Remi, CEMAGREF, Antony, France.
  • Nordström Ernst, University of Uppsala, Sweden, ernstn@docs.uu.se
  • Nowè Ann, Vrije Universiteit Brussel, Belgium, asnowe@info.vub.ac.be
  • Patel Mukesh, Institute of Computer Science, FORTH, Heraklion, Greece, patel@elet.polimi.it
  • Peres Simon, University of Edinburgh, United Kingdom, simonpe@aisb.ed.ac.uk
  • Piola Roberto, Universitá di Torino, Italy, piola@di.unito.it
  • Rafal Salustowicz, Lugano, Switzerland, rafal@zucca.idsia.ch
  • Saurel Pierre, CEMAGREF, Antony, France, saurel@poly.polytechnique.fr
  • Schmidhuber JuergenIDSIA, Lugano, Switzerland, juergen@idsia.ch
  • Versino CristinaIDSIA, Lugano, Switzerland, versino@idsia.ch
  • Wyatt Jeremy, University of Edinburgh, United Kingdom, jeremyw@aifh.ed.ac.uk
  • Zhang Ping, Université de Technologie de Compiegne, France, pzhang@hds.univ-compiegne.fr


    List of Hotels

    The participants should book directly the Hotels. A list is provided in the following.

    Hotel CITTA’ STUDI – via Saldini 24
    Tel. +39.2.744666 – 744620 – FAX +39.2713122
    Single: Itl: 90.000 – Double: 120.000 – triple: 162.000 No breakfast – 2stars

    Hotel LOMBARDIA – via Lombardia 74
    Tel . +39.2.2892515 – 26110551 – FAX: +39.2.2893430
    Single: itl: 120.000 – Double: 180.000 – Triple: 235.OOO Breakfast incl.-3stars

    Hotel LUGANO – via Astolfo 6
    Tel. +39.2.2663000 – Fax +39.2.26680317
    Single: Itl: 110.000 – Doubel: 160.000 – Triple: 200.000 Breakfast incl. -3stars

    Hotel ZEFIRO – via Gallina 12
    Tel. +39.2.7384253 – Fax +39.2.713811
    Single: Itl: 122.000 – Double: 172.000 – Triple: 205.000 – NO Breakfast- 3stars

    Hotel GAMMA – via Valvassori Peroni 85
    Tel. +39.2.26414116 – 26414120 – Fax +39.2.2640255
    Single: Itl: 120.000 – Double: 180.000 – Triple: 210.000 – Breakfast incl. 3stars



    Intention Form


    Second European Workshop on Reinforcement Learning (EWRL-2)

    Milano, Italy, September 18-19, 1995

    I intend to participate and will give a presentation with the following tentative title:

    Family Name:

    First Name:




    Phone No.:

    Fax No.:



    %d bloggers like this: