Monte Carlo Search 2020, IJCAI Workshop, Japan, January 2021

In conjunction with IJCAI 2020

The proceedings will be published with Springer in their Communications in Computer and Information Science series CCIS.

Schedule

Go to workshop 15 in virtual room Yellow South 1 IJCAI virtual conference site

January 7, 8am - 1pm UTC

8:00-8:05 Opening: Mark Winands

8:05-8:25 Erwan Le Merrer and Adel Jaouen, zoNNscan: A boundary-entropy index for zone inspection of neural models

8:25-8:45 Tobias Joppen and Johannes Furnkranz, Ordinal Monte Carlo Tree Search

8:45-9:05 Tristan Cazenave and Veronique Ventos, The AlphaMu Search Algorithm for the Game of Bridge

9:05-9:25 Tristan Cazenave, Monte Carlo Game Solver

9:25-9:45 Break

9:45-10:05 Tristan Cazenave, Generalized Nested Rollout Policy Adaptation

10:05-10:25 Florian Geisser, David Speck and Thomas Keller, Trial-based Heuristic Tree Search for MDPs with Factored Action Spaces

10:25-10:45 Sunandita Patra, James Mason, Amit Kumar, Malik Ghallab, Paolo Traverso and Dana Nau, Integrating Acting, Planning, and Learning in Hierarchical Operational Models

10:45-11:05 Tristan Cazenave and Thomas Fournier, Monte Carlo Inverse Folding

11:05-11:30 Break

11:30-11:50 Tristan Cazenave, Jean-Baptiste Sevestre and Matthieu Toulemont, Stabilized Nested Rollout Policy Adaptation

11:50-12:10 Tristan Cazenave, Benjamin Negrevergne and Florian Sikora, Monte Carlo Graph Coloring

12:10-12:30 Chiara F. Sironi, Tristan Cazenave and Mark H. M. Winands, Enhancing Playout Policy Adaptation for General Game Playing

12:30-12:45 Closing: Tristan Cazenave

DESCRIPTION

Monte Carlo Search is a family of general search algorithms that have many applications in different domains.

It is the state of the art in perfect and imperfect information games.

Other applications include the RNA inverse folding problem, Logistics, Multiple Sequence Alignment, General Game Playing, Puzzles, 3D Packing with Object Orientation, Cooperative Pathfinding, Software testing and heuristic Model-Checking.

In recent years, many researchers have explored different variants of the algorithms, their relations to Deep Reinforcement Learning and their different applications.

The purpose of this workshop is to bring these researchers together to present their research, discuss future research directions, and cross-fertilize the different communities.

Researchers and practitioners whose research might benefit from Monte Carlo Search in their research are welcome.

Monte Carlo Tree Search, and then Zero learning vastly improved Monte Carlo search in a wide range of applications; classic Monte Carlo search still dominates many partially observable problems.

Submissions are welcome in all fields related to Monte Carlo Search, including:

ACCEPTED PAPERS

Erwan Le Merrer and Adel Jaouen, zoNNscan: A boundary-entropy index for zone inspection of neural models

Tobias Joppen and Johannes Furnkranz, Ordinal Monte Carlo Tree Search

Tristan Cazenave and Veronique Ventos, The AlphaMu Search Algorithm for the Game of Bridge

Tristan Cazenave, Monte Carlo Game Solver

Tristan Cazenave, Generalized Nested Rollout Policy Adaptation

Florian Geisser, David Speck and Thomas Keller, Trial-based Heuristic Tree Search for MDPs with Factored Action Spaces

Sunandita Patra, James Mason, Amit Kumar, Malik Ghallab, Paolo Traverso and Dana Nau, Integrating Acting, Planning, and Learning in Hierarchical Operational Models

Tristan Cazenave and Thomas Fournier, Monte Carlo Inverse Folding

Tristan Cazenave, Jean-Baptiste Sevestre and Matthieu Toulemont, Stabilized Nested Rollout Policy Adaptation

Tristan Cazenave, Benjamin Negrevergne and Florian Sikora, Monte Carlo Graph Coloring

Chiara F. Sironi, Tristan Cazenave and Mark H. M. Winands, Enhancing Playout Policy Adaptation for General Game Playing

SUBMISSION GUIDELINES

Papers are written in English using LNCS style.

IMPORTANT DATES

Second Submission Deadline: September 1st, 2020

Notification: September 21st, 2020

Final Papers: TBA

MCS 2020: January, 2021

PAPER SUBMISSION

You can submit your papers using this link to Easychair

GENERAL CHAIRS

Tristan Cazenave, Universite Paris-Dauphine, PSL

Olivier Teytaud, Facebook FAIR

Mark Winands, Maastricht University

PROGRAM COMMITTEE

Yngvi Bjornsson Reykjavik University

Bruno Bouzy Nukkai

Cameron Browne Maastricht University

Tristan Cazenave University Paris-Dauphine

Stefan Edelkamp King's College London

Raluca Gaina Queen Mary University of London

Aurelien Garivier ENS Lyon

Reijer Grimbergen Tokyo University of Technology

Nicolas Jouandeau University Paris 8

Emilie Kaufmann CNRS

Jakub Kowalski University of Wroclaw

Marc Lanctot Google DeepMind

Jialin Liu Southern University of Science and Technology

Martin Mueller University of Alberta

Andrzej Nagorko University of Warsaw

Benjamin Negrevergne University Paris-Dauphine

Santiago Ontanon Drexel University

Diego Perez-Liebana Queen Mary University of London

Mike Preuss Leiden University

Thomas Runarsson University of Iceland

Abdallah Saffidine University of New South Wales

Spyridon Samothrakis University of Essex

Chiara Sironi Maastricht University

Fabien Teytaud Universite Littoral Cote d'Opale

Olivier Teytaud Facebook FAIR

Ruck Thawonmas Ritsumeikan University

Jean-Noel Vittaut Sorbonne University

Mark Winands Maastricht University

I-Chen Wu National Chiao Tung University