• 11 July 2018: The ALA 2018 Best Paper Award will be sponsored by Valeo
• 16 May 2018: Submissions are now closed. We received 55 submissions this year!
• 14 May 2018: The submission deadline has been extended to 15 May 2018 23:59 UTC!
• 19 April 2018: The submission deadline has been extended to 13 May 2018!
• 7 March 2018: Program Committee members added
• 27 February 2018: ALA 2018 site launched

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 year's edition of ALA will be held as part of the joint workshop program at the Federated AI Meeting (FAIM) which will take place in Stockholm. Co-located conferences at the FAIM include AAMAS, ICML, IJCAI-ECAI, ICCBR and SOCS.

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

• ALA-17
• ALA-16
• ALA-15
• ALA-14
• ALA-13
• ALA-12
• ALA-11
• ALA-10
• ALA-09
• ALAMAS+ALAg-08
• ALAg-07
• Earlier editions

The goal of this workshop is to increase awareness of 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 multi-agent systems. It aims at bringing together not only scientists from different areas of computer science (e.g. agent architectures, reinforcement learning, 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 of ongoing or completed work covering both theoretical and practical aspects of adaptive and learning agents and multi-agent systems.

This workshop will focus on all aspects of adaptive and learning agents and multi-agent 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 multi-agent learning
• Reinforcement learning (single- and multi-agent)
• Novel deep learning approaches for adaptive single- and multi-agent systems
• Multi-objective optimisation in single- and multi-agent systems
• Planning (single- and multi-agent)
• Reasoning (single- and multi-agent)
• Distributed learning
• Adaptation and learning in dynamic environments
• Evolution of agents in complex environments
• Co-evolution of agents in a multi-agent setting
• Cooperative exploration and learning to cooperate and collaborate
• Learning trust and reputation
• Communication restrictions and their impact on multi-agent 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 multi-agent systems
• Game theoretical analysis of adaptive multi-agent systems
• Neuro-control in multi-agent systems
• Bio-inspired multi-agent systems
• Applications of adaptive and learning agents and multi-agent systems to real world complex systems

Extended and revised versions of papers presented at the workshop will be eligible for inclusion in a journal special issue (see below).

• Submission Deadline: 22 April 2018    extended to 15 May 2018 23:59 UTC
• Notification of acceptance: 29 May 2018    13 June 2018
• Camera-ready copies: 12 June 2018    27 June 2018
• Workshop: 14/15 July 2018

Papers can be submitted through EasyChair.

We invite submission of original work, up to 8 pages in length (excluding references) in the ACM proceedings format (i.e. following the AAMAS formatting instructions). This includes work that has been accepted as a poster/extended abstract at any of the FAIM 2018 conferences. Additionally, we welcome submission of preliminary results, i.e. work-in-progress, as well as visionary outlook papers that lay out directions for future research in a specific area, both up to 6 pages in length, although shorter papers are very much welcome, and will not be judged differently. Finally, we also accept recently published journal papers in the form of a 2 page abstract.

All submissions will be peer-reviewed (single-blind). Accepted work will be allocated time for oral presentation during the workshop. Papers accepted at the workshop will also be eligible for inclusion in a special issue published after the workshop.

We are delighted to announce that extended versions of all original contributions at ALA 2018 will be eligible for inclusion in a special issue of The Knowledge Engineering Review (Impact Factor 1.510). The deadline for submitting extended papers will be 1 October 2018.

We will post further details about the submission process and expected publication timeline here after the workshop.

Saturday 14 July (Location: Room B4)

Sunday 15 July (Location: Room B4)

The papers which are accepted for a poster presentation only are listed below. Authors who have either a long or short talk may optionally also present it in poster form, during the poster session on the same day as their talk is scheduled.

Poster Session A - Saturday 14 July 16:00 to 18:00

• Caroline Player and Nathan Griffiths. Addressing Concept Drift in Reputation Assessment
• Di Wu, Guillaume Rabusseau, Vincent François-Lavet, Doina Precup and Benoit Boulet. Optimizing Home Energy Management and Electric Vehicle Charging with Reinforcement Learning
• Mathieu Reymond, Christophe Patyn, Roxana Radulescu, Geert Deconinck and Ann Nowe. Reinforcement Learning for Demand Response of Domestic Household Appliances
• Xinlei Pan, Eshed Ohn-Bar, Nicholas Rhinehart, Yan Xu, Yilin Shen and Kris M. Kitani. Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning
• Tambet Matiisen, Aqeel Labash, Daniel Majoral, Jaan Aru and Raul Vicente. Do deep reinforcement learning agents model intentions?
• Dustin Dannenhauer, Michael Floyd, Matthew Molineaux and David Aha. Learning from Exploration: Towards an Explainable Goal Reasoning Agent
• Oliver Roesler and Ann Nowé. Simultaneous Action Learning and Grounding through Reinforcement and Cross-Situational Learning

Poster Session B - Sunday 15 July 16:00 to 18:00

• Aleksandra Malysheva, Aleksei Shpilman and Daniel Kudenko. Learning to Run with Reward Shaping from Video Data
• John Burden and Daniel Kudenko. Using Uniform State Abstractions For Reward Shaping With Reinforcement Learning
• Gabriel de La Cruz, Yunshu Du and Matthew Taylor. Pre-training Neural Networks with Human Demonstrations for Deep Reinforcement Learning
• Francis Lawlor, Rem Collier and Vivek Nallur. Towards a Programmable Framework for Agent Game Playing
• Su Zhang and Matthew Taylor. Enhanced Learning from Multiple Demonstrations with a Two-level Structured Approach
• Golden Rockefeller, Scott Chow, Yathartha Tuladhar and Kagan Tumer. Policy Progress Score for Automatic Task Selection in Curriculum Learning
• David Isele and Kikuo Fujimura. The Sidewalk Problem

Shimon Whiteson

Affiliation: University of Oxford

Website: https://www.cs.ox.ac.uk/people/shimon.whiteson/

Bio: Shimon Whiteson is an Associate Professor in the Department of Computer Science at the University of Oxford and the Chief Scientist and Co-Founder of Latent Logic Ltd. His research focuses on deep reinforcement learning and learning from demonstration, with applications in robotics and video games. He completed his doctorate at the University of Texas at Austin in 2007. He spent eight years as an Assistant and then an Associate Professor at the University of Amsterdam before joining Oxford as an Associate Professor in 2015. He was awarded a Starting Grant from the European Research Council in 2014 and a Google Faculty Research Award in 2017.

Talk Title: Cooperative Multi-Agent Reinforcement Learning

Kagan Tumer

Affiliation: Oregon State University

Website: http://web.engr.oregonstate.edu/~ktumer/

Bio: Dr. Kagan Tumer is the Director of Collaborative Robotics and Intelligent Systems (CoRIS) Institute at Oregon State University. His research focuses on long term autonomy and AI in unstructured environments, with an emphasis on "what" AI systems need to do rather than "how" they do it. His work has been applied to multi-robot coordination, air traffic management, and unmanned aerial vehicle control. Kagan received his PhD from The University of Texas, Austin, and spent nine years at NASA Ames Research Center as a researcher and group lead. His work has led to one patent and over two hundred publications, including three edited books and best paper awards (AAMAS 2007, GECCO 2012). He is an associate editor of the Journal on Autonomous Agents and Multiagent Systems, and was the program co-chair of the 2011 Autonomous Agents and Multiagent Systems Conference (AAMAS 2011).

Talk Title: Current State and Future of AI: Separating Fact from Fiction

• Baris Akgün, Koç University, TR
• Adrian Agogino, NASA Ames Research Center, USA
• Roland Bouffanais, Singapore University of Technology and Design, SG
• Tim Brys, Vrije Universiteit Brussel, BE
• Jen Jen Chung, Eidgenössische Technische Hochschule Zürich, CH
• Chad Crawford, University of Tulsa, USA
• William Curran, Oregon State University, USA
• Felipe Leno da Silva, University of São Paulo, BR
• Sam Devlin, Microsoft Research, UK
• Kyriakos Efthymiadis, Vrije Universiteit Brussel, BE
• Ahmad A. Al Sallab, Valeo, EG
• Matthew Gombolay, Massachusetts Institute of Technology, USA
• Brent Harrison, Georgia Institute of Technology, USA
• Mark Ho, Brown University, USA
• B. Ravi Kiran, AKKA, FR
• Richard Klima, University of Liverpool, UK
• Matt Knudson, NASA Ames Research Center, USA
• Pieter Liblin, Vrije Universiteit Brussel, IE
• Robert Loftin, North Carolina State University, USA
• Patrick MacAlpine, University of Texas at Austin, USA
• Marlos Machado, University of Alberta, CA
• Kleanthis Malialis, University of Cyprus, CY
• Karl Mason, National University of Ireland Galway, IE
• Felipe Meneguzzi, Pontifícia Universidade Católica do Rio Grande do Sul, BR
• Paul Miller, Glasgow Neuro LTD, UK
• Enrique Munoz de Cote, PROWLER.io, UK
• Roxana Radulescu, Vrije Universiteit Brussel, BE
• Carrie Rebhuhn, Oregon State University, USA
• Gabriel Ramos, Vrije Universiteit Brussel, BE
• Diederik Roijers, Vrije Universiteit Brussel, BE
• Fernando P. Santos, Technical University of Lisbon, PT
• Francisco Santos, Universidade de Lisboa, PT
• Aleksei Shpilman, JetBrains Research, RU
• Jivko Sinapov, Tufts University, USA
• Ibrahim Sobh, Valeo, EG
• Peter Vamplew, Federation University Australia, AU
• Timothy Verstraeten, Vrije Universiteit Brussel, BE
• Senthil Yogamani, Valeo Vision Systems, IE

• Anna Harutyunyan (DeepMind, UK)
• Patrick Mannion (Galway-Mayo Institute of Technology, IE)
• Bei Peng (Washington State University, USA)
• Kaushik Subramanian (Georgia Institute of Technology, USA)

• Enda Howley (National University of Ireland Galway, IE)
• Daniel Kudenko (University of York, UK)
• Ann Nowé (Vrije Universiteit Brussel, BE)
• 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)

The ALA 2018 Best Paper Award is kindly sponsored by Valeo.

If you have any questions about the ALA workshop, please contact the organizers at:
ala.workshop.2018 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: