Stimulated by emerging applications, such as those powered by the Internet of the Things, critical infrastructure network, and security games, intelligent agents commonly leverage different forms optimization and/or learning to solve complex problems.
The goal of the workshop is to provide researchers with a venue to discuss techniques for tackling a variety of multi-agent optimization problems. We seek contributions in the general area of multi- agent optimization, including distributed optimization, coalition formation, optimization under uncertainty, winner determination algorithms in auctions, and algorithms to compute Nash and other equilibria in games. This year, the workshop will have a special focus on contributions at the intersection of optimization and learning. For example, agents which use optimization often employ machine learning to predict unknown parameters appearing in their decision problem. Or, machine learning techniques may be used to improve the efficiency of optimization. While submissions across the spectrum of multi-agent optimization are welcome, contributions at the intersection with learning are especially encouraged.


This workshop invites works from different strands of the multi-agent systems community that pertain to the design of algorithms, models, and techniques to deal with multi-agent optimization and learning problems or problems that can be effectively solved by adopting a multi-agent framework.
The workshop is of interest both to researchers investigating applications of multi-agent systems to optimization problems in large, complex domains, as well as to those examining optimization and learning problems that arise in systems comprised of many autonomous agents. In so doing, this workshop aims to provide a forum for researchers to discuss common issues that arise in solving optimization and learning problems in different areas, to introduce new application domains for multi-agent optimization techniques, and to elaborate common benchmarks to test solutions.

Topics of Interest

  • Optimization for learning agents
  • Learning for multiagent optimization problems
  • Distributed constraint satisfaction and optimization
  • Winner determination algorithms in auctions
  • Coalition formation algorithms
  • Algorithms to compute Nash and other equilibria in games
  • Optimization under uncertainty
  • Optimization with incomplete or dynamic input data
  • Algorithms for real-time applications
  • GPU for general purpose computations (GPGPU)
  • Multi-core and many-core computing
  • Cloud, distributed and grid computing

Submission Information

Conference submission site:
Submissions should conform to the AAMAS-20 template

Submissions should include the name(s), affiliations, and email addresses of all authors. We welcome the submission of papers rejected from the AAMAS 2020 technical program.
Submissions will be refereed on the basis of technical quality, novelty, significance, and clarity. Each submission will be thoroughly reviewed by at least two program committee members.

Submission Types

  • Long Papers: Full-length research papers detailing work in progress or work that could potentially be published at a major conference. These papers should not exceed *7* pages in AAMAS format (excluding bibliography and appendices).
  • Short Papers: Position or demo papers that describe initial work or an application that has not yet been evaluated on the topics of interest. These papers should not exceed *4* pages in the AAMAS format (excluding bibliography and appendices).

For questions about the submission process, contact the workshop co-chairs.

Important Dates

Due to the Covid-19 there are strong delays on the workshop timeline. We will announce notification and further instructions as soon as possible. Please check the Covid-19 News at the AAMAS-20 website for updated information.
  • Submission Deadline: 25 February 2020 (Extended)
  • Notification of acceptance: 10 March 2020
  • Workshop: 8 May 2020

Technical Program

Friday, May 8.
All Times are in Eastern Time Zone (UTC−05:00)
Session 1: Resource allocation and scheduling in multiagent systems 11:00 - 11:20: Breakout Room Session 1

Session 2: Game Theory
  • 11:20: Scalable Game-Focused Learning of Adversary Models: Data-to-Decisions in Network Security Games
  • screencast link | | Breakout Room
  • 11:35: Robust Self-organization in Games: Symmetries, Conservation Laws and Dimensionality Reduction
  • screencast link | Breakout Room
  • 11:50: Game Theory for Strategic DDoS Mitigation
  • Breakout Room
  • 12:00: Infinite population evolutionary dynamics match infinite memory reinforcement learning dynamics
  • Breakout Room
  • 12:10: Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning
  • screencast link | Breakout Room
12:20 - 12:40: Breakout Room Session 2

Session 3: Reinforcement Learning 13:50 - 14:10: Breakout Room Session 3

Session 4: Multiagent cooperation and decentralized algorithms 15:20 - 16:30: Breakout Room Session 4

Invited Speaker

Pradeep Varakantham

screencast link
Bio: Pradeep Varakantham is an Associate Professor in the School of Information Systems at Singapore Management University. His research is at the intersection of Artificial Intelligence, Operations Research and Machine Learning with specific focus on solving (multi-agent) sequential planning/learning problems. Pradeep has published extensively in top tier conferences and journals in Artificial Intelligence and Machine Learning. Apart from publishing his research, he has led translational projects that have been successfully deployed and in use by multiple government agencies pertaining to transportation, safety and security in Singapore. He is a senior member of Association for Advancement of Artificial Intelligence (AAAI), gave the "early career spotlight” invited talk at International Joint Conference on Artificial Intelligence, IJCAI 2016, has received google research award for projects on “ AI for Social Good”. His papers have won the best application, best-demo and finalist at ICAPS-19, AAMAS-2018 and INFORMS Innovative Applications in Analytics awards respectively.

Accepted Papers

  • Kai Wang, Andrew Perrault, Aditya Mate and Milind Tambe.
    Scalable Game-Focused Learning of Adversary Models: Data-to-Decisions in Network Security Games
  • Sai Ganesh Nagarajan, David Balduzzi and Georgios Piliouras.
    Robust Self-organization in Games: Symmetries, Conservation Laws and Dimensionality Reduction
  • Sanket Shah, Meghna Lowalekar and Pradeep Varakantham.
    Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
  • Qi Zhang, Ed Durfee and Satinder Singh.
    Efficient Querying for Cooperative Commitments
  • Jeroen Fransman, Joris Sijs, Henry Dol, Erik Theunissen and Bart De Schutter.
    The Distributed Bayesian algorithm: simulation and experimental results for a cooperative multi UAV search use-case
  • Amit Sarker, Abdullahil Baki Arif, Moumita Choudhury and Md.
    Mosaddek Khan.
    C-CoCoA: A Continuous Cooperative Constraint Approximation Algorithm to Solve Functional DCOPs
  • Rose Wang, Sarah Wu, Max Kleiman-Weiner, David Parkes, James Evans and Josh Tenenbaum.
    Too many cooks: Coordinating multi-agent collaboration through inverse planning
  • Nate Gruver, Jiaming Song, Mykel Kochenderfer and Stefano Ermon.
    Multi-agent Adversarial Inverse Reinforcement Learning with Latent Variables
  • Sanket Shah, Arunesh Sinha, Pradeep Varakantham, Andrew Perrault and Milind Tambe.
    Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning
  • Dhaval Adjodah, Dan Calacci, Abhimanyu Dubey, Anirudh Goyal, Peter Krafft, Esteban Moro and Alex Pentland.
    Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning
  • Hang Xu, Ridhima Bector and Zinovi Rabinovich.
    Teaching Multiple Learning Agents by Environment-Dynamics Tweaks
  • Athina Georgara, Carles Sierra and Juan Antonio Rodrigues-Aguilar.
    TAIP: an anytime algorithm for allocating student teams to internship programs
  • Yu Wang, Yilin Shen and Hongxia Jin.
    Design of a Multimodal VQA System with Weighted Contextual Features
  • Filippo Bistaffa, Juan Antonio Rodriguez Aguilar and Jesus Cerquides.
    Predicting Requests in Large-Scale Online P2P Ridesharing
  • Vinayak Dubey, Nirav Ajmeri, Pankaj Telang and Munindar Singh.
    Effective Defense Against Cybersecurity Attacks Using Reinforcement Learning
  • Aditya Mate, Jackson Killian, Andrew Perrault, Haifeng Xu and Milind Tambe.
    Building Decision Aids for CommunityHealth Workers: Optimizing Interventions via Restless Bandits
  • Elnaz Shafipour, Matheus Aparecido Do Carmo Alves, Leandro Soriano Marcolino and Plamen Angelov.
    Decentralised Task Allocation in the Fog: Estimators for Effective Ad-hoc Teamwork
  • Pankaj Mishra, Takayuki Ito and Ahmed Maustafa.
    Fairness based Multi-Preference Resource Allocation in Decentralised Open Markets
  • Jhelum Chakravorty, Nadeem Ward, Julien Roy, Maxime Chevalier-Boisvert, Sumana Basu, Andrei Lupu and Doina Precup.
    Option-critic in cooperative multi-agent systems
  • Fumito Uwano and Keiki Takadama.
    Directionality Reinforcement Learning to Operate Multi-Agent System without Communication
  • Wolfram Barfuss.
    Infinite population evolutionary dynamics match infinite memory reinforcement learning dynamics
  • Omkar Thakoor, Minlan Yu, Milind Tambe and Phebe Vayanos.
    Game Theory for Strategic DDoS Mitigation

Program Committee


Workshop Co-Chairs:
contact us

Past Editions