gaips_bea image1 image2 image3 image4 image5 gaips_ecute_beach_bar_banner gaips_ecute_train_incorrect_ticket_banner
Francisco S. Melo Email icon Webpage icon

Degree :
PhD
Institution :
INESC-ID
Address :
IST Tagusparque, Av. Prof. Dr. Cavaco Silva, 2744-016 Porto Salvo, Portugal
Office :
2N7.15
Telephone :
+351 210 407 002

Interests

I am an assistant professor at the Department of Computer Science and Engineering of Instituto Superior Técnico, in Lisbon, Portugal.

In my research, I am interested in the application of machine learning in the development of general intelligent autonomous agents capable of interacting with complex, possibly unknown environments. Concretely, my primary research interests are in general reinforcement learning both in single and multiagent systems and in the applications of this framework to real world problems, including robotic and sensor network applications. I am also particularly interested in developing computational models that may contribute to a better understanding of learning in biological systems.


Current Projects
Geometry Friends AI competition PArCEIRO INSIDE AMIGOS


Publications

  Associate Latent Encodings in Learning from Demonstrations
pdf iconbib icon
Hang Yin and Francisco S. Melo and Aude Billard and Ana Paiva, Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI). San Francisco, California, USA., 2017

“ Me and You Together ” Movement Impact in Multi-user Collaboration Tasks
pdf iconbib icon
Miguel Faria and Rui Silva and Patricia Alves-Oliveira and Francisco S. Melo and Ana Paiva, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pg. 2793--2798, IEEE, Vancouver, BC, Canada, September, 2017

  Dynamics of Fairness in Groups of Autonomous Learning Agents
pdf iconbib icon
Fernando P. Santos and Francisco C. Santos and Francisco S. Melo and Ana Paiva and Jorge M. Pacheco, Autonomous Agents and Multiagent Systems, AAMAS 2016 Workshops Best Papers, pg. 107-126, Vol. 10002, Springer International Publishing, 2016

Discovering Social Interaction Strategies for Robots from Restricted-Perception Wizard-of-Oz Studies
pdf iconbib icon
Pedro Sequeira and Patrícia Alves-Oliveira and Tiago Ribeiro and Eugenio Di Tullio and Sofia Petisca and Francisco S. Melo and Ginevra Castellano and Ana Paiva, , pg. 197--204, 2016

Just follow the suit! Trust in Human-Robot Interactions during Card Game Playing
pdf iconbib icon
Filipa Correia and Patrícia Alves-Oliveira and Nuno Maia and Tiago Ribeiro and Sofia Petisca and Francisco S. Melo and Ana Paiva, IEEE RO-MAN 2016, New York, USA., 2016

Learning to be Fair in Multiplayer Ultimatum Games (Extended Abstract)
pdf iconbib icon
Fernando P. Santos and Francisco C. Santos and Francisco S. Melo and Ana Paiva and Jorge M. Pacheco, Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems , pg. 1381-1382 , IFAAMAS, 2016

Multiplayer ultimatum game in populations of autonomous agents
pdf iconbib icon
Fernando P. Santos and Francisco C. Santos and Francisco S. Melo and Ana Paiva and Jorge M. Pacheco, Proceedings of Adaptive and Learning Agents Workshop (ALA 2016), part of 2016 Int. Conf. Autonomous Agents and Multiagent Systems (AAMAS 2016), (Best paper award), 2016

Rapidly-Exploring Random Tree approach for Geometry Friends
pdf iconbib icon
Rui Miguel Barata Castanho Soares and Francisco Leal and Rui Prada and Francisco S. Melo, Proceedings of the First International Joint Conference of DIGRA and FDG, 2016

Synthesizing Robotic Handwriting Motion by Learning from Human Demonstrations
pdf iconbib icon
Hang Yin and Patrícia Alves-Oliveira and Francisco S. Melo and Aude Billard and Ana Paiva, Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), July 09-15, 2016

  "It's amazing, We Are All Feeling it!" Emotional Climate as a Group-Level Emotional Expression in HRI
bib icon
Patrícia Alves-Oliveira and Pedro Sequeira and Eugenio Di Tullio and Sofia Petisca and Carla Guerra and Francisco S. Melo and Ana Paiva, AAAI Fall Symposium, 2015

A Reinforcement Learning Approach for the Circle Agent of Geometry Friends
pdf iconbib icon
João Quitério and Rui Prada and Francisco S. Melo, CIG’2015 - IEEE Conference on Computational Intelligence and Games, pg. 423-430, IEEE Computer Society, Tainan, Taiwan, August, 2015

An Empathic Robotic Tutor for School Classrooms: Considering Expectation and Satisfaction of Children as End-Users
bib icon
Patrícia Alves-Oliveira and Tiago Ribeiro and Sofia Petisca and Eugenio Di Tullio and Francisco S. Melo and Ana Paiva, In Social Robotics, pg. 21-30, Springer International Publishing, 2015

The Development of Cooperation in Evolving Populations through Social Importance
pdf iconbib icon
Pedro Sequeira and Samuel Mascarenhas and Francisco S. Melo and Ana Paiva, Proceedings of the 5th International Conference on Development and Learning and on Epigenetic Robotics, pg. 308--313, IEEE Computer Society, Providence, Rhode Island, Aug, 2015

The Geometry Friends Game AI Competition
pdf iconbib icon
Rui Prada and Phil Lopes and João Catarino and João Quitério and Francisco S. Melo, CIG’2015 - IEEE Conference on Computational Intelligence and Games, pg. 431-438, IEEE Computer Society, Tainan, Taiwan, August, 2015

The “Favors Game”: A Framework to Study the Emergence of Cooperation through Social Importance ( Extended Abstract )
pdf iconbib icon
Pedro Sequeira and Samuel Mascarenhas and Francisco S. Melo and Ana Paiva, Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, pg. 1899--1900, Istanbul, Turkey, May, 2015

“Let's Save Resources!”: A Dynamic, Collaborative AI for a Multiplayer Environmental Awareness Game
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva, Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games, pg. 399--406, IEEE Computer Society, Tainan, Taiwan, Aug-Sept, 2015

  Emergence of emotional appraisal signals in reinforcement learning agents
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva, Autonomous Agents and Multi-Agent Systems, April, 2014

Learning by Appraising: An Emotion-based Approach for Intrinsic Reward Design
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva, Adaptive Behavior, Vol. 22, No. 5, pg. 330-349, October, 2014

  An Associative State-Space Metric for Learning in Factored MDPs
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva, Proceedings of the 16th Portuguese Conference on Artificial Intelligence, pg. 163-174, Springer-Verlag, Berlin Heidelberg , September, 2013

Emergence of Emotion-Like Signals in Learning Agents
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva

Towards agents with human-like decisions under uncertainty
pdf iconbib icon
Nuno Marques and Francisco S. Melo and Samuel Mascarenhas and João Dias and Rui Prada and Ana Paiva, Cogsci 2013- The annual Meeting of the Cognitive Science Society, 2013

  Associative metric for learning in factored MDPs based on classical conditioning
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva

Decentralized Multiagent Planning for Balance Control in Smart Grids
bib icon
Francisco S. Melo and Alberto Sardinha and Stefan Witwicki and Laura M. Ramirez-Elizondo and Matthijs T. J. Spaan, International Workshop on Information Technology for Energy Applications (IT4ENERGY 2012), September, 2012

Exploiting Sparse Interactions for Optimizing Communication in Dec-MDPs
pdf iconbib icon
Francisco S. Melo and Matthijs Spaan and Stefan Witwicki, Proceedings of the Workshop on Multiagent Sequential Decision Making Under Uncertainty (MSDM-2012), pg. 40-47, June, 2012

Learning by Appraising: An emotion-based approach for intrinsic reward design
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva

  Emerging social awareness: Exploring intrinsic motivation in multiagent learning
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Rui Prada and Ana Paiva, Proceedings of the First Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, pg. 1--6, IEEE, 2011

Emotion-Based Intrinsic Motivation for Reinforcement Learning Agents (Best Paper Award)
pdf iconbib icon
Pedro Sequeira and Francisco S. Melo and Ana Paiva, Affective Computing and Intelligent Interaction (ACII 2011), pg. 326-336, Springer Berlin / Heidelberg, 2011

  Abstraction levels for robotic imitation: Overview and computational approaches
bib icon
Manuel Lopes and Francisco S. Melo and Luis Montesano and José Santos-Victor, Abstraction Levels for Robotic Imitation: Overview and Computational Approaches, pg. 313-355, Springer, Olivier Sigaud and Jan Peters (Eds.), 2010

A computational model of object affordances
bib icon
Luis Montesano and Manuel Lopes and Francisco S. Melo and Alexandre Bernardino and José Santos-Victor, Advances in Cognitive Systems, IET Publishers, Samia Nefti-Meziani and John Gray (Eds.), 2010

Analysis of inverse reinforcement learning with perturbed demonstrations
pdf iconbib icon
Francisco S. Melo and Manuel Lopes and Ricardo Ferreira, Proceedings of the 19th European Conference on Artificial Intelligence, pg. 349-354, 2010

Approximate planning for decentralized MDPs with sparse interactions (Extended Abstract)
pdf iconbib icon
Francisco S. Melo and Manuela Veloso, Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems, pg. 1389-1390, 2010

Coordinated learning in multiagent MDPs with infinite state spaces
pdf iconbib icon
Francisco S. Melo and M. Isabel Ribeiro, Journal of Autonomous Agents and Multiagent Systems , Vol. 21, No. 3, pg. 321-367, 2010

Heuristic planning for decentralized MDPs with sparse interactions
pdf iconbib icon
Francisco S. Melo and Manuela Veloso, Proceedings of the 10th International Symposium on Distributed Autonomous Robotics Systems, 2010

Learning from demonstration using MDP induced metrics
pdf iconbib icon
Francisco S. Melo and Manuel Lopes, Proceedings of the 2010 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pg. 385-401, 2010

Machine optimisation of dynamic gait parameters for bipedal walking
pdf iconbib icon
Martin Mason and Peter Gibbons and Manuel Lopes and Francisco S. Melo, Proceedings of the 11th Conference Towards Autonomous Robotic Systems, pg. 154-160, 2010

 
bib icon
Manuel Lopes and Francisco S. Melo and Ben Kenward and José Santos-Victor, A computational model of social-learning mechanisms, pg. 467-483, Chap. 6, Vol. 17, Adaptive Behavior, 2009

Active learning for reward estimation in inverse reinforcement learning
pdf iconbib icon
Manuel Lopes and Francisco S. Melo and Luis Montesano, Proceedings of the 2009 European Conference on Machine Learning and Practice of Knowledge Discovery in Databases, pg. 31-46, 2009

Learning of coordination: Exploiting sparse interactions in multiagent systems
pdf iconbib icon
Francisco S. Melo and Manuela Veloso, Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems, pg. 773-780, IFAAMAS, 2009

MODEN: Obstacle-driven elastic network for line-of-sight communication
pdf iconbib icon
Francisco S. Melo and Manuela Veloso, Proceedings of the 14th Portuguese Conference on Artificial Intelligence, pg. 254-266, 2009