News

  • September 30, Post-proceedings deadline extended
  • July 30, ALA Post-proceedings submissions are now open
  • April 30, ALA Workshop Program Online
  • April 23, ALA Linkedin Group Created
  • April 20, ALA12 Invited Speakers Announced
  • April 20, ALA12 Proceedings online
  • April 16, List of accepted papers online
  • April 5, Camera ready copies can now be uploaded to easychair
  • March 30, Notifications sent
  • March 20, ALA extended to 1.5 day workshop
  • March 10, Submissions closed
  • February 24, Submission Deadline Extended
  • February 16, PC announced.
  • December 19, ALA-12 site launched.

ALA 2012 - Workshop at AAMAS 2012

Adaptive Learning Agents encompasses diverse fields such as Computer Science, Software Engineering, Biology, as well as Cognitive and Social Sciences. The ALA workshop will focus on agents and multiagent systems which employ learning or adaptation.

This workshop is a continuation of the long running AAMAS series of workshops on adaptive agents, now in its twelfth year. Previous editions of this workshop may be found at the following urls:


The goal of this workshop is to increase awareness and interest in adaptive agent research, encourage collaboration and give a representative overview of current research in the area of adaptive and learning agents and multiagent systems. It aims at bringing together not only scientists from different areas of computer science (e.g., agent architectures, reinforcement learning, and evolutionary algorithms) but also from different fields studying similar concepts (e.g., game theory, bio-inspired control, mechanism design).

The workshop will serve as an inclusive forum for the discussion on ongoing or completed work in both theoretical and practical issues of adaptive and learning agents and multiagent systems.


This workshop will focus on all aspects of adaptive and learning agents and multiagent systems with a particular emphasis on how to modify established learning techniques and/or create new learning paradigms to address the many challenges presented by complex real-world problems. The topics of interest include but are not limited to:

  • Novel combinations of reinforcement and supervised learning approaches
  • Integrated learning approaches that work with other agent reasoning modules like negotiation, trust models, coordination, etc.
  • Supervised multiagent learning
  • Reinforcement learning (single and multiagent)
  • Planning (single and multiagent)
  • Reasoning (single and multiagent)
  • Distributed learning
  • Adaptation and learning in dynamic environments
  • Evolution of agents in complex environments
  • Co-evolution of agents in a multiagent setting
  • Cooperative exploration and learning to cooperate and collaborate
  • Learning trust and reputation
  • Communication restrictions and their impact on multiagent coordination
  • Design of reward structure and fitness measures for coordination
  • Scaling learning techniques to large systems of learning and adaptive agents
  • Emergent behaviour in adaptive multiagent systems
  • Game theoretical analysis of adaptive multiagent systems
  • Neuro-control in multiagent systems
  • Bio-inspired multiagent systems
  • Applications of adaptive and learning agents and multiagents systems to real world complex systems
  • Learning of Co-ordination

Accepted papers from the workshop will be eligible to be extended for inclusion in a special issue of the The Knowledge Engineering Review journal which is published by Cambridge Journals. A review cycle is scheduled for Summer 2012, details will be provided on this workshop site at that stage.

Submission

Authors of papers presented at the workshop can now submit extended and revised versions of their papers for inclusion in a special issue of the Knowledge Engineering Review, published by Cambridge Journals. All ALA 2012 papers are eligible for consideration for this special issue. Since only a relatively small fraction of papers can be accepted for the special issue, we are also looking into additional publication options for ALA post-proceedings. Provided there are sufficient levels of interest and the standard of unsuccessful papers is high enough, we will offer authors the opportunity to publish their paper in a special post-proceedings book. This will also be contingent on the agreement of a publisher. We are currently in negotiations with publishers and more details on this book will be announced later.

All ALA 2012 authors interested in either the special issue or post-proceedings book are requested to register their paper as soon as possible using the online form at the following link: Post-Proceedings Registration

All reviews will be conducted using a double blind review process. You are asked not to identify yourself in your paper submission through either including your name at the top of the paper or throughout the text by referring to your previous papers. Such papers should simply be referenced in the normal way as papers relevant to the topic being discussed.You are asked to format your submission using the Knowledge Engineering Review formatting instructions . Papers for KER Special Issues do not typically have an upper page limit, but we ask authors to keep their papers in the range of 20-30 pages. All papers are to be uploaded to Easychair (note new url!) by the submission deadline. Please make careful consideration of the reviewers comments received during the ALA review process and also the feedback received during the workshop presentations.

Important Dates

  • Submission Deadline
February 28, 2012 March 11, 2012  
  • Notification of acceptance:
March 27, 2012 March 30, 2012
  • Camera-ready copies:
April 10, 2012  
  • Workshop:
June 4-5, 2012  
  • Post-proceedings submission Deadline:
October 1, 2012 October 15, 2012  

Invited Talks

The ALA workshop will have two invited talks from leading academics in the domain of Multi-Agent Systems.

Professor Michael Luck

Department of Informatics

King's College London

Website


Professor Simon Parsons

Department of Computer and Information Science

Brooklyn College

City University of New York

Website

Venue

The ALA workshop will be held at AAMAS 2012, the eleventh International Conference on Autonomous Agents and Multiagent Systems which will take place in Valencia, Spain.

Registration

Registration is handled directly by AAMAS.

Proceedings

The ALA2012 proceedings can be downloaded here.

Program

The detailed ALA Program can be downloaded here


Accepted Papers:
Gracaliz Dimuro and Antonio Costa. Regulation of Social Exchanges in Open MAS: the problem of reciprocal conversions between POMDPs and HMMs
Daniel Villatoro, Giulia Andrighetto, Jordi Brandts, Jordi Sabater Mir and Rosaria Conte. Learning with more than rewards: The Implicit Signalling of Distributed Punishment
Abdel Rodriguez, Peter Vrancx, Ricardo Grau and Ann Nowe. A Reinforcement Learning Approach to Coordinate Exploration with Limited Communication in Continuous Action Games
Olivier Georgeon and Sakellariou Ilias. Designing Environment-Agnostic Agents
Monica Pinol, Angel Sappa, Angeles Lopez and Ricardo Toledo. Feature Selection Based on Reinforcement Learning for Object Recognition
Lisa Torrey and Matthew Taylor. Help an Agent Out: Student/Teacher Learning in Sequential Decision Tasks
Sam Devlin and Daniel Kudenko. Plan-Based Reward Shaping for Multi-Agent Reinforcement Learning
Samuel Barrett, Peter Stone, Sarit Kraus and Avi Rosenfeld. Learning Teammate Models for Ad Hoc Teamwork
Kyriakos Efthymiadis, Sam Devlin and Daniel Kudenko. Overcoming Incorrect Knowledge in Plan-Based Reward Shaping
Yann-Michael De Hauwere, Sam Devlin, Daniel Kudenko and Ann Nowe. Context sensitive reward shaping in a loosely coupled multi-agent system
David Catteeuw and Bernard Manderick. Emergence of Honest Signaling through Reinforcement Learning
Yujing Hu, Yang Gao, Ruili Wang, Zhaonan Sun and Xingguo Chen. nMetaQ: An n-agent Reinforcement Learning Algorithm Based on Meta Equilibrium
Scott Proper and Kagan Tumer. Coordination Graphs in Continuous Domains for Multiagent Reinforcement Learning
Chris Holmesparker and Kagan Tumer. Combining Difference Rewards and Hierarchies for Scaling to Large Multiagent Systems
Kleanthis Malialis and Daniel Kudenko. Reinforcement Learning of Throttling for DDoS Attack Response
Sam Ganzfried and Tuomas Sandholm. Safe Opponent Exploitation
Todd Hester and Peter Stone. Intrinsically Motivated Model Learning for a Developing Curious Agent
Landon Kraemer and Bikramjit Banerjee. Informed Initial Policies for Learning in Finite Horizon Dec-POMDPsInformed Initial Policies for Learning in Finite Horizon Dec-POMDPs
Mohamed Elidrisi, Nicholas Johnson and Maria Gini. Fast Learning against Adaptive Adversarial Opponents
Eunkyung Kim, Yu-Han Chang, Rajiv Maheswaran, Yu Ning and Luyan Chi. Adaptive Agents in Dynamic Games: Negotiating in Diverse Societies
Patrick Macalpine and Peter Stone. Using Dynamic Rewards to Learn a Fully Holonomic Bipedal Walk
Matthew Adams, Robert Loftin, Matthew Taylor, Michael Littman and David Roberts. An Empirical Analysis of RL's Drift From Its Behaviorism Roots
Carrie Rebhuhn and Kagan Tumer. Fast Multiagent Learning from Actions Not Taken for Heterogeneous Agents
Atil Iscen and Kagan Tumer. Multiagent Learning of choices via simpler MDPs and Reward Shaping

Program Committee

  • Adrian Agogino, UCSC, NASA Ames Research Center, USA
  • Bikramjit Banerjee, The University of Southern Mississippi, USA
  • Enda Barrett, National University of Ireland, Ireland
  • Samuel Barrett,University of Texas at Austin, USA
  • Ana L.C. Bazzan, Universidade Federal do Rio Grande do Sul, Brazil
  • David Catteeuw, Vrije Universiteit Brussels, Belgium
  • Vincent Corruble, University of Paris 6, France
  • Yann-Michaël De Hauwere, Vrije Universiteit Brussels, Belgium
  • Sam Devlin, University of York, UK
  • Marek Grzes, University of Waterloo, Canada
  • Daniel Hennes, Maastricht University, The Netherlands
  • Todd Hester, University of Texas at Austin, USA
  • Chris Holmes Parker, Oregon State University, USA
  • Atil Iscen, Oregon State University, USA
  • Shivaram Kalyanakrishnan, Yahoo Labs Bangalore, India
  • Franziska Klugl, University of Orebro, Sweden
  • W. Bradley Knox, University of Texas at Austin, USA
  • Daniel Kudenko, University of York, UK
  • Mihail Mihailov, Vrije Universiteit Brussels, Belgium
  • Ann Nowe, Vrije Universiteit Brussels, Belgium
  • Liviu Panait, Google Inc Santa Monica, USA
  • Matthew Taylor, Lafayette College, USA
  • Karl Tuyls, Maastricht University, The Netherlands
  • Logan Yliniemi, Oregon State University, USA

Organization

This year's workshop is organized by:

Questions about the ALA workshop should be directed to the chairs by email:


Senior Steering Committee Members:
  • Franziska Klugl (University of Orebro, Sweden)
  • Daniel Kudenko (University of York, UK)
  • Ann Nowe (Vrije Universiteit Brussels, Belgium)
  • Lynne E. Parker (University of Tennessee, USA)
  • Sandip Sen (University of Tulsa, USA)
  • Peter Stone (University of Texas at Austin, USA)
  • Kagan Tumer (Oregon State University, USA)
  • Karl Tuyls (Maastricht University, The Netherlands)

Contact

For inquiries please feel free to contact the chairs by e-mail:


For more general news, discussion, collaboration and networking opportunities with others interested in Adaptive Learning Agents then please join our Linkedin Group