Doctoral Consortium Program

 

The schedule and the links to the virtual rooms are provided at

     https://underline.io/events/288/schedule?day=2022-05-10T22%3A00%3A00.000Z&trackId=1488

Monday, May 9

New York Time (Eastern Daylight Time) UTC-4

Auckland Time (New Zealand Standard Time) UTC+12

Program

Presenters

Format

07:00 am – 07:30 am 11:00 pm – 11:30 pm Opening + Introductions + Ice Breakers
+ 1 min slide (for the students to introduce themselves)
Co-Chairs Live
07:30 am – 8:45 am 11:30 pm – 12:45 am

Humans and AI / Human-Agent Interaction + Robotics

Student Presentations (10 min + 5 min Q&A); 5 talks

Students
Embodied Team Intelligence in Multi-Robot Systems

Esmaeil Seraj (Georgia Institute of Technology)

Towards Multi-Agent Interactive Reinforcement Learning for Opportunistic Software Composition in Ambient Environments Kevin Delcourt (IRIT, University of Toulouse)
Collaborative Training of Multiple Autonomous Agents Filippos Christianos (University of Edinburgh)
Empathetic Reinforcement Learning Agents Manisha Senadeera (Deakin University)
Non-Cooperative Multi-Robot Planning Under Shared Resources Anna Gautier (University of Oxford)
15 min Break
9:00 am – 10:15 am 1:00 am – 2:15 am

Learning and Adaptation

Student Presentations (10 min + 5 min Q&A); 5 talks

Students Live
Transferable Environment Poisoning: Training-time Attack on Reinforcement Learner with Limited Prior Knowledge Hang Xu (Nanyang Technological University)
Model-free and model-based reinforcement learning, the intersection of learning and planning Piotr Januszewski (Gdansk University of Technology)
Task Generalisation in Multi-Agent Reinforcement Learning Lukas Schäfer (University of Edinburgh)
Exploration and Communication for Partially Observable Collaborative Multi-Agent Reinforcement Learning

Raphaël Avalos (Vrije Universiteit Brussel)

Online learning against Strategic Adversary

Le Cong Dinh (University of Southampton)

15 min Break

10:30 am – 11:45 am

2:30 am – 3:45 am

Markets, Auctions, and Non-Cooperative Game Theory + Social Choice

Student Presentations (10 min + 5 min Q&A); 5 talks

Manipulation of Machine Learning Algorithms

Nicholas Bishop (University of Southampton)

Fair Allocation Problems in Reviewer Assignment

Justin Payan (University of Massachusetts Amherst)

Budget Feasible Mechanisms in Auction Markets: Truthfulness, Diffusion and Fairness

Xiang Liu (Southeast University)

Incentive Design for Equitable Resource Allocation: Artificial Currencies and Allocation Constraints

Devansh Jalota (Stanford University)

Designing Mechanisms for Participatory Budgeting

Simon Rey (University of Amsterdam)

15 min Break

12:00 pm – 1:15 pm

4:00 am – 5:15 am

Keynote Talk

Virginia Dignum (Umeå University)

Speaker

Live

15 min Break

1:30 pm – 2:45 pm

5:30 am – 6:45 am

Engineering Multiagent Systems +
Modelling and Simulation of Societies +
Knowledge Representation, Reasoning, and Planning Coordination, Organisations, Institutions, and Norms + Innovative Applications
Student Presentations (10 min + 5 min Q&A); 5 talks

Students Live

The coaching scenario: Recommender Systems with a long term goal. A Case Study in Changing Dietary Habits

Jules Vandeputte (INRAE, Agroparistech)

 

Data-driven approaches for formal synthesis of dynamical systems

Milad Kazemi (Newcastle University)

Using multi-objective optimization to generate timely responsive BDI agents

Marcio F. Stabile Junior (University of São Paulo)

The Reputation Lag Attack

Sean Sirur (University of Oxford)

Engineering Normative and Cognitive Agents with Emotions and Values

Sz-Ting Tzeng (North Carolina State University)

15 min Break
3:00 pm – 4:15 pm 7:00 am – 8:15 am

Panel (Career Panel)

Maria Gini (University of Minnesota)Sandip Sen (University of Tulsa)Peter Stone (University of Texas at Austin)Manuela Veloso (Carnegie Mellon University)

 

Panelists Live
4:15 pm – 4:30 pm 8:15 am – 8:30 am Closing
4:30 pm – 6:00 pm

8:30 am – 10:00 am

Virtual Social: Meet and Greet All Live

Keynote Talk

Virginia Dignum (Umeå University)

Title: Principles for responsible AI: trustworthy, relational, contextual

Abstract:

The impact of Artificial Intelligence does not depend only on fundamental research and technological developments, but for a large part on how these systems are introduced into society and used in everyday situations. Even though AI is traditionally associated with rational decision making, understanding and shaping the societal impact of AI in all its facets requires a relational perspective. A rational approach to AI, where computational algorithms drive decision making independent of human intervention, insights and emotions, has shown to result in bias and exclusion, laying bare societal vulnerabilities and insecurities. A relational approach, that focus on the relational nature of things, is needed to deal with the ethical, legal, societal, cultural, and environmental implications of AI. A relational approach to AI recognises that objective and rational reasoning cannot does not always result in the ‘right’ way to proceed because what is ‘right’ depends on the dynamics of the situation in which the decision is taken, and that rather than solving ethical problems the focus of design and use of AI must be on asking the ethical question.

In this talk, I start with a general discussion of current conceptualisations of AI followed by an overview of existing approaches to governance and responsible development and use of AI. Then, I reflect over what should be the bases of a social paradigm for trustworthy AI and how this should be embedded in relational, feminist and non-Western philosophies.

Mentors

 

Christopher Amato  Northeastern University 
Reshef Meir  Technion-Israel Institute of Technology 
Michele Flammini  Gran Sasso Science Institute 
Fang Fei  Carnegie Mellon University 
Haris Aziz  UNSW Sydney and Data61 CSIRO 
Daniel Hennes  Google 
Marc Lanctot  DeepMind 
Amos Azaria  Ariel University 
Ioannis Caragiannis  Aarhus University 
Frans Oliehoek  Delft University of Technology 
Kobi Gal  Ben-Gurion University and University of Edinburgh 
Tibor Bosse  Radboud Universiteit 
Mathijs de Weerdt  Delft University of Technology 
Bo Li  University of Illinois at Urbana-Champaign 
Jakob Foerster  University of Oxford 
Adish Singla  Max Planck Institute for Software Systems 
Özgür Şimşek  University of Bath 
Rafael H. Bordini  School of Technology, PUCRS 
Pınar Yolum  Utrecht University 
Julian Padget  University of Bath 

Accepted Papers

# Title Authors
1 Embodied Team Intelligence in Multi-Robot Systems Esmaeil Seraj
2 Fair Allocation Problems in Reviewer Assignment Justin Payan
3 Budget Feasible Mechanisms in Auction Markets: Truthfulness, Diffusion and Fairness Xiang Liu
4 Transferable Environment Poisoning: Training-time Attack on Reinforcement Learner with Limited Prior Knowledge Hang Xu
5 Incentive Design for Equitable Resource Allocation: Artificial Currencies and Allocation Constraints Devansh Jalota
6 Model-free and model-based reinforcement learning, the intersection of learning and planning Piotr Januszewski
7 Task Generalisation in Multi-Agent Reinforcement Learning Lukas Schäfer
8 Towards Multi-Agent Interactive Reinforcement Learning for Opportunistic Software Composition in Ambient Environments Kevin Delcourt
9 Designing Mechanisms for Participatory Budgeting Simon Rey
10 Collaborative Training of Multiple Autonomous Agents Filippos Christianos
11 The coaching scenario: Recommender Systems with a long term goal. A Case Study in Changing Dietary Habits Jules Vandeputte
12 Empathetic Reinforcement Learning Agents Manisha Senadeera
13 Non-Cooperative Multi-Robot Planning Under Shared Resources Anna Gautier
14 Data-driven approaches for formal synthesis of dynamical systems Milad Kazemi
15 Exploration and Communication for Partially Observable Collaborative Multi-Agent Reinforcement Learning Raphaël Avalos
16 Manipulation of Machine Learning Algoirhtms Nicholas Bishop
17 Online learning against Strategic Adversary Le Cong Dinh
18 Using multi-objective optimization to generate timely responsive BDI agents Marcio F. Stabile Junior
19 The Reputation Lag Attack Sean Sirur
20 Engineering Normative and Cognitive Agents with Emotions and Values Sz-Ting Tzeng

Doctoral Consortium Programme Committee (Reviewers)

Name Affiliation
Diana Francisca Adamatti Universidade Federal do Rio Grande
Christopher Amato Northeastern University
Leila Amgoud IRIT – CNRS
Francesco Amigoni Politecnico di Milano
Bo An Nanyang Technological University
Ofer Arieli The Academic College of Tel-Aviv
Haris Aziz UNSW Sydney and Data61 CSIRO
Matteo Baldoni Dipartimento di Informatica, Univ. di Torino
Timothy Bickmore Northeastern University
Célia da Costa Pereira Université Côte d’Azur
John Dickerson University of Maryland
Edith Elkind University of Oxford
Fei Fang Carnegie Mellon University
Christopher Frantz Norwegian University of Science and Technology
Enrico Gerding University of Southampton
Maria Gini University of Minnesota
Dirk Heylen University of Twente
Hannes Högni Vilhjálmsson Reykjavik University
Jérôme Lang CNRS, LAMSADE, Université Paris-Dauphine
Victor Lesser University of Massachusetts Amherst
Bo Li University of Illinois at Urbana-Champaign
Dominique Longin CNRS, IRIT
Michael Luck King’s College London
Reshef Meir Technion-Israel Institute of Technology
Frans Oliehoek Delft University of Technology
Simon Parsons University of Lincoln
David Pynadath University of Southern California
Jordi Sabater Mir IIIA-CSIC
Sebastian Sardina RMIT University
Silvia Schiaffino ISISTAN, Instituto Superior de Ingeniería de Software Tandil (CONICET – UNCPBA)
Francois Schwarzentruber École normale supérieure de Rennes
Sandip Sen University of Tulsa
Arunesh Sinha Singapore Management University
Mohan Sridharan University of Birmingham
Samarth Swarup University of Virginia
Paolo Torroni University of Bologna
Long Tran-Thanh University of Warwick
Harko Verhagen Dept. of Computer and Systems Sciences, Stockholm University
Makoto Yokoo Kyushu University