News

  • 9 May 2016: the ALA proceedings are now available to download
  • 5 April 2016: the preliminary program is now online!
  • 18 March 2016: we are happy to announce our invited speaker for this year, dr. Peter Vamplew.
  • 9 February 2016: Submission is now closed, we are happy to have received 21 papers this year!
  • 21 January 2016: submission deadline extended to February 8!
  • 18 November 2015: ALA 2016 site launched

Social Event

The ALA social event will be held on Monday 9 May, starting at 7:30pm at The Quay Kitchen and Bar. The bar serves food as well, for those in need of dinner.

ALA 2016 - Workshop at AAMAS 2016

Adaptive Learning Agents (ALA) 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 fourteenth 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 amphasis 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

Accepted papers from the workshop will be eligible to be extended for inclusion in a special issue journal.

Important Dates

  • Submission Deadline: February 8, 2016
  • Notification of acceptance: March 7, 2016
  • Camera-ready copies: March 10, 2016
  • Workshop: May 9/10, 2016

Program

The ALA proceedings can be downloaded here.

Monday 9 May

09:00 - 10:30 Welcome & Session I - Chair: Logan Yliniemi
09:00 - 09:15 Opening
09:15 - 09:40 Patrick Mannion, Sam Devlin, Jim Duggan and Enda Howley:
Avoiding the Tragedy of the Commons using Reward Shaping
09:40 - 10:05 Patrick Mannion, Karl Mason, Sam Devlin, Jim Duggan and Enda Howley:
Dynamic Economic Emissions Dispatch Optimisation using Multi-Agent Reinforcement Learning
10:05 - 10:30 Jonathan Grizou, Samuel Barrett, Peter Stone and Manuel Lopes:
Collaboration in Ad Hoc Teamwork: Ambiguous Tasks, Roles, and Communication
10:30 - 11:00 Coffee Break
11:00 - 12:30 Session II - Chair: Mihail Mihaylov
11:00 - 11:25 Shamin Kinathil, Scott Sanner, Sanmay Das and Nicolas Della Penna:
Optimal Adaptive Market-Making with Inventory: A Symbolic Closed-form Solution
11:25 - 11:50 Barnabé Monnot and Georgios Piliouras:
Limits and Limitations of No-Regret Learning in Games
11:50 - 12:15 Fernando P. Santos, Francisco C. Santos, Francisco S. Melo, Ana Paiva and Jorge M. Pacheco:
Multiplayer ultimatum game in populations of autonomous agents
12:15 - 12:30 Filipo Studzinski Perotto, Umberto Grandi and Stéphane Airiau:
Learning Agents for Iterative Voting
12:30 - 14:00 Lunch
14:00 - 15:30 Keynote & Session III - Chair: Tim Brys
14:00 - 15:00 Invited speaker: Peter Vamplew
Preventing the Robot Apocalypse (and other reasons that we need multiobjective reinforcement learning)
15:00 - 15:25 Thanh Nguyen, Arunesh Sinha, Shahrzad Gholami, Andrew Plumptre, Lucas Joppa, Milind Tambe, Margaret Driciru, Fred Wanyama, Aggrey Rwetsiba, Rob Critchlow and Colin Beale:
CAPTURE: A New Predictive Anti-Poaching Tool for Wildlife Protection
15:30 - 16:00 Coffee Break
16:00 - 17:00 Session IV: Work in Progress & Outlook - Chair: Daan Bloembergen
16:00 - 16:15 Guangliang Li and Bo He:
Reinforcement Learning from Demonstration and Human Reward
16:15 - 16:30 David Isele, José Marcio Luna, Eric Eaton, Gabriel V. De La Cruz, James Irwin, Brandon Kallaher and Matthew E. Taylor:
Lifelong Learning for Disturbance Rejection on Mobile Robots
16:30 - 16:45 Timothy Verstraeten, Roxana Radulescu, Yannick Jadoul, Tom Jaspers, Robrecht Conjaerts, Tim Brys, Anna Harutyunyan, Peter Vrancx and Ann Nowé:
Human Guided Ensemble Learning in StarCraft
16:45 - 17:00 Logan Yliniemi and Kagan Tumer:
Outlook: Using Awareness to Promote Richer, More Human-Like Behaviors in Artificial Agents
17:00 - 17:30 Community meeting
19:30 - ... ALA Social Event

Tuesday 10 May

09:00 - 10:30 Session V - Chair: Patrick Mannion
09:00 - 09:25 Sierra Adibi, Scott Forer, Jeremy Fries and Logan Yliniemi:
Autonomous UAV Landing in Windy Conditions with MAP-Elites
09:25 - 09:50 Matthew Hausknecht, Prannoy Mupparaju, Sandeep Subramanian, Shivaram Kalyanakrishnan and Peter Stone:
Half Field Offense: An Environment for Multiagent Learning and Ad Hoc Teamwork
09:50 - 10:15 Matthew Hausknecht, Yilun Chen and Peter Stone:
Deep Imitation Learning for Parameterized Action Spaces
10:15 - 10:30 Farzaneh Shoeleh and Masoud Asadpour:
TLDA: Transfer Learning via Domain Adaptation in Continuous Reinforcement Learning Domains
10:30 - 11:00 Coffee Break
11:00 - 12:30 Session VI & Closing - Chair: Fernando Santos
11:00 - 11:15 Joe Collenette, Katie Atkinson, Daan Bloembergen and Karl Tuyls:
Mobility effects on the evolution of co-operation in emotional robotic agents
11:15 - 11:30 Karl Mason, Patrick Mannion, Jim Duggan and Enda Howley:
Applying Multi-Agent Reinforcement Learning to Watershed Management
11:30 - 11:45 Kleanthis Malialis, Jun Wang, Gary Brooks and George Frangou:
Feature Selection as a Multiagent Coordination Problem
11:45 - 12:30 Closing remarks, awards, announcements, and ALA 2017

Invited Talk

Dr. Peter Vamplew

Federation University Australia

Website

Bio: Peter Vamplew is an Associate Professor in Information Technology at Federation University Australia, and co-leader of the Federation Learning Agents Group. Over the last decade he has been one of the leading researchers driving the emergence of MORL as a distinct and important sub-area of reinforcement learning research.

Preventing the Robot Apocalypse
(and other reasons that we need multiobjective reinforcement learning)

Abstract: While traditional reinforcement learning approaches assume a scalar reward, many real-world problems actually exhibit multiple, conflicting objectives. Multiobjective reinforcement learning (MORL) is an emerging area of research, aimed at extending reinforcement learning methods to address tasks with multiple objectives. This presentation will provide an overview of MORL, starting from a definition of the formalisms underpinning MORL, and using three general scenarios to illustrate situations where scalar reinforcement learning methods may not be applicable. In particular the task of developing ethically-constrained intelligent agents will be considered as a driving case for the development of MORL methods. The state-of-the-art in MORL algorithms will also be reviewed, providing guidance on existing approaches for practitioners, and identifying remaining challenges for MORL research.

Program Committee

  • Adrian Agogino, University of California Santa Cruz, USA
  • Nolan Bard, University of Alberta, CAN
  • Enda Barrett, National University of Ireland, Galway, IRL
  • Haitham Bou Ammar, Princeton University, USA
  • Bastian Bröcker, University of Liverpool, UK
  • Jen Jen Chung, Oregon State University, USA
  • Daniel Claes, University of Liverpool, UK
  • William Curran, Oregon State University, USA
  • Sam Devlin, University of York, UK
  • Kyriakos Efthymiadis, University of York, UK
  • Joscha Fossel, University of Liverpool, UK
  • Anna Harutyunyan, VU Brussel, BE
  • Daniel Hennes, DFKI, DE
  • Enda Howley, National University of Ireland, Galway, IRL
  • Michael Kaisers, CWI, NL
  • Sepideh Kharaghani, Oregon State University, USA
  • Matt Knudson, NASA Ames Research Center, USA
  • Patrick MacAlpine, University of Texas at Austin, USA
  • Kleanthis Malialis, University College London, UK
  • Carrie Rebhuhn, Oregon State University, USA
  • Kaushik Subramanian, Georgia Institute of Technology, USA
  • Peter Vrancx, VU Brussel, BE

Organization

This year's workshop is organized by:
Senior Steering Committee Members:
  • Daniel Kudenko (University of York, UK)
  • Ann Nowé (Vrije Universiteit Brussels, Belgium)
  • Sandip Sen (University of Tulsa, USA)
  • Peter Stone (University of Texas at Austin, USA)
  • Matthew Taylor (Washington State University, USA)
  • Kagan Tumer (Oregon State University, USA)
  • Karl Tuyls (University of Liverpool, UK)

Contact

If you have any questions about the ALA workshop, please contact the organizers at:
ala.workshop.2016 AT gmail.com

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