Francisco Melo

Francisco Melo

Former Collaborator

This author has not yet filled in any details.

Closed Projects

Acronym Name Funding Dates
RESCUE Cooperative Navigation for Rescue Robots FCT 2000|2004

Journal Papers

[1] Francisco Melo, Alberto Sardinha, David Belo, Marta Couto, Miguel Faria, Anabela Farias, H. Gamboa, Cátia Jesus, Mithun Kinarullathil, Pedro Lima, Luís Luz, André Mateus, Isabel Melo, Plinio Moreno, Daniel Osório, A. Paiva, Jhielson Pimentel, João Rodrigues, Pedro Sequeira, Rubén Solera-Ureña, Miguel Vasco, Manuela Veloso, Rodrigo Ventura, Project INSIDE: Towards Autonomous Semi-Unstructured Human-Robot Social Interaction in Autism Therapy, Journal Artificial Intelligence in Medicine 2018, 2018
[2] S. Witwicki, J. C. Castillo, João Messias, J. Capitan, Francisco Melo, Pedro Lima, Manuela Veloso, Autonomous Surveillance Robots: A Decision-Making Framework for Networked Multiagent Systems, IEEE Robotics and Automation Magazine, 24(3), pp 52-64, September, 2017 - PDF
[3] Isabel Ribeiro, Francisco Melo, Coordinated Learning in Infinite Markov Games, Autonomous Agents and Multiagent Systems, Vol. 21, Nº 3, November 2010, pp.321-367, 2010
[4] B. Kenward, A Computational Model of Social-Learning Mechanisms, Adaptive Behaviour, 17(6), pp. 467-483, 2009

Book Chapters

[5] Luis Montesano, Manuel Lopes, Francisco Melo, Alexandre Bernardino, José Santos-Victor, A Computational Model of Object Affordances, Advances in Cognitive Systems, S.Nefti and J.O.Gray, (Eds.), IET, pp. 87-126, 2010
[6] Manuel Lopes, Luis Montesano, Francisco Melo, José Santos-Victor, Abstraction Levels for Robotic Imitation: Overview and Computational Approaches, From motor to interaction learning in robots, Olivier Sigaud & Jan Peters (Eds.), Vol. 264, pp. 313-355, Springer, 2010
[7] Francisco Melo, Isabel Ribeiro, Q-learning with linear function approximation, Learning Theory: 20th Annual Conference on Learning Theory, Lecture Notes in Artificial Intelligence, vol. 4539, pp. 308-322, Springer-Verlag, 2007 - PDF

Conference Papers

[8] S. D. Klee, Beatriz Ferreira, R. silva, João Paulo Costeira, Francisco Melo, M. Veloso, Personalized Assistance for Dressing Users, Proc. of ICSR 2015 - International Conference on Social Robotics, Paris, France. LNCS, Vol. 9388, pp. 359-369; doi: 10.1007/978-3-319-25554-5_36, 2015 - PDF
[9] S. Witwicki, J. C. Montoya, João Messias, J. Reis, Jesús Capitán, Francisco Melo, Pedro Lima, Matthijs Spaan, A Testbed for Autonomous Robot Surveillance (Demonstration), Proc. of AAMAS 2014 - 13th International Conference on Autonomous Agents and Multiagent Systems, pp. 1635-1636, Paris, France, 2014 - PDF
[10] Manuel Lopes, Active Learning for Reward Estimation in Inverse Reinforcement Learning, Proc. of ECML/PKDD 2009 - European Conference on Machine Learning, Bled, Slovenia, 2009 - PDF
[11] B. Kenward, A computational model for social learning mechanisms, Proc. of IROS 2008 - Workshop From motor to interaction learning in robots, Nice, France, 2008
[12] S. P. Meyn, An analysis of reinforcement learning with function approximation, Proc. of ICML 2008 - International Conference on Machine Learning, Helsinki, CA, Finland, 2008 - PDF
[13] Manuel Lopes, Fitted natural actor-critic: A new algorithm for continuous state-action MDPs, Proc. of ECML PKDD 2008 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Antwerp, Belgium, 2008 - PDF
[14] Francisco Melo, Emerging coordination in infinite team Markov games, Proc. of AAMAS 2008 - 7th International Joint Conference on Autonomous Agents and Multi-Agent Systems, Estoril, Portugal, 2008 - PDF
[15] Francisco Melo, Reinforcement learning with function approximation for cooperative navigation tasks, Proc. of the ICRA 2008 - IEEE International Conference on Robotics and Automation, Pasadena, CA, USA, pp. 3321-3327, 2008 - PDF
[16] Francisco Melo, Interaction-Driven Markov Games for Decentralized Multiagent Planning under Uncertainty, Proc. of AAMAS 2008 - the 7th International Conference on Autonomous Agents and Multiagent Systems, Estoril, Portugal, 2008 - PDF
[17] Manuel Lopes, Machine learning for developmental robotics, Proc. of NIPS 2007 - The 21st Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 2007
[18] Francisco Melo, Policy gradient approach to multi-robot, Proc. of NIPS 2007 - The 21st Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 2007
[19] Francisco Melo, Manuel Lopes, Convergence of Independent Adaptive Learners, Proc. of EPIA 2007 - 13th Portuguese Conference on Artificial Intelligence, Guimaraes, Portugal, 2007 - PDF
[20] Francisco Melo, Q-Learning and Function Approximation, Proc. of COLT2007 - 20th Annual Conference on Learning Theory, San Diego, California, USA, 2007 - PDF
[21] Francisco Melo, Learning to Coordinate in Topological Navigation Tasks, Proc. of IAV2007 - 6th IFAC Symposium on Intelligent Autonomous Vehicles, Toulouse, France, 2007 - PDF
[22] Manuel Lopes, Affordance-based imitation learning in robots, Proc. of IROS 2007 - IEEE/RSJ International Conference on Intelligent Robots and Systems, San Diego, California, USA, 2007
[23] Francisco Melo, A POMDP approach to cooperative localization in sparse environments, Proc. of RobotMat2007 - Workshop on Robotics and Mathematics, Coimbra, Portugal, 2007 - PDF
[24] Francisco Melo, Convergence of Q-learning with linear function approximation, Proc. of ECC2007 - European Control Conference, Kos International Convention Centre, Kos, Greece, pp.2671-2678, 2007 - PDF
[25] Manuel Lopes, Unified framework for imitation-like behaviors, Proc. of AISB2007 - 4th International Symposium on Imitation in Animals and Artifacts, pp. 241-250, Newcastle University, Newcastle upon Tyne, United Kingdom, 2007 - PDF
[26] M. Veloso, MODEN: Multi-Robot, Obstacle-Driven Elastic Network Path Planning, Proc. ROBOTICA 2007 - 7th Portuguese Conference on Mobile Robots and Competitions, Paderne, Algarve, Portugal, 2007 - PDF
[27] Francisco Melo, Transition Entropy in Partially Observable Markov Decision Processes, Proc. IAS9 - 9th Intelligent Autonomous Systems, Tokyo, Japan, 2006 - PDF
[28] Francisco Melo, Isabel Ribeiro, Pedro Lima, Navigation Controllability of a Mobile Robot Population, Proc. RoboCup 2004 Symposium, Lisbon, Portugal, 2004 - PDF
[29] Francisco Melo, Pedro Lima, Isabel Ribeiro, Event-driven Modelling and Control of a Mobile Robot Population, Proc. IAS8 - 8th Conference on Intelligent Autonomous Systems, Amsterdam, The Netherlands. pp. 237-244, 2004 - PDF

PhD Theses

[30] Francisco Melo, Reinforcement Learning in Cooperative Navigation Tasks, Ph.D. Thesis, Instituto Superior Tecnico, Universidade Tecnica de Lisboa, Portugal, 2007 - PDF

Technical Reports

[31] Francisco Melo, Isabel Ribeiro, Q-learning with linear function approximation, Technical Report RT-602-07, Institute for Systems and Robotics, Instituto Superior Tecnico, 2007
[32] Francisco Melo, Manuel Lopes, Convergence of independent adaptive learners, Technical Report RT-603-07, Institute for Systems and Robotics, Instituto Superior Tecnico, 2007
[33] Francisco Melo, Rational and convergent model-free adaptive learning for team Markov games, Technical Report RT-601-07, Institute for Systems and Robotics, Instituto Superior Tecnico, 2007 - PDF
[34] Francisco Melo, Isabel Ribeiro, Convergence of Classical Reinforcement Learning Algorithms and Partial Observability, Technical Report RT-601-06, Institute for Systems and Robotics, Instituto Superior Tecnico, 2006
[35] Francisco Melo, Isabel Ribeiro, Convergence Results for Reinforcement Learning with Partial Observability, Technical Report RT-602-05, Institute for Systems and Robotics, Instituto Superior Tecnico, 2005
[36] Francisco Melo, Isabel Ribeiro, The Use of Transition Entropy in Partially Observable Markov Decision Processes, Technical Report RT-601-05, Instituto for Systems and Robotics, Instituto Superior Tecnico, 2005 - PDF
[37] Alexandre Bernardino, Luís Custódio, João Frazão, Pedro Lima, Francisco Melo, Isabel Ribeiro, José Santos-Victor, Alberto Vale, RESCUE Project Final Report, ISR Technical Report, 2004
[38] Francisco Melo, Isabel Ribeiro, Pedro Lima, Blocking Controllability of a Mobile Robot Population, Relatorio Tecnico, RT-601-04, Instituto de Sistemas e Robotica, Polo do Instituto Superior Tecnico, 2004 - PDF
[1] Francisco Melo, Alberto Sardinha, David Belo, Marta Couto, Miguel Faria, Anabela Farias, H. Gamboa, Cátia Jesus, Mithun Kinarullathil, Pedro Lima, Luís Luz, André Mateus, Isabel Melo, Plinio Moreno, Daniel Osório, A. Paiva, Jhielson Pimentel, João Rodrigues, Pedro Sequeira, Rubén Solera-Ureña, Miguel Vasco, Manuela Veloso, Rodrigo Ventura, Project INSIDE: Towards Autonomous Semi-Unstructured Human-Robot Social Interaction in Autism Therapy, Journal Artificial Intelligence in Medicine 2018, 2018
[2] S. Witwicki, J. C. Castillo, João Messias, J. Capitan, Francisco Melo, Pedro Lima, Manuela Veloso, Autonomous Surveillance Robots: A Decision-Making Framework for Networked Multiagent Systems, IEEE Robotics and Automation Magazine, 24(3), pp 52-64, September, 2017 - PDF
[3] Isabel Ribeiro, Francisco Melo, Coordinated Learning in Infinite Markov Games, Autonomous Agents and Multiagent Systems, Vol. 21, Nº 3, November 2010, pp.321-367, 2010
[4] B. Kenward, A Computational Model of Social-Learning Mechanisms, Adaptive Behaviour, 17(6), pp. 467-483, 2009
[1] Luis Montesano, Manuel Lopes, Francisco Melo, Alexandre Bernardino, José Santos-Victor, A Computational Model of Object Affordances, Advances in Cognitive Systems, S.Nefti and J.O.Gray, (Eds.), IET, pp. 87-126, 2010
[2] Manuel Lopes, Luis Montesano, Francisco Melo, José Santos-Victor, Abstraction Levels for Robotic Imitation: Overview and Computational Approaches, From motor to interaction learning in robots, Olivier Sigaud & Jan Peters (Eds.), Vol. 264, pp. 313-355, Springer, 2010
[3] Francisco Melo, Isabel Ribeiro, Q-learning with linear function approximation, Learning Theory: 20th Annual Conference on Learning Theory, Lecture Notes in Artificial Intelligence, vol. 4539, pp. 308-322, Springer-Verlag, 2007 - PDF
[1] S. D. Klee, Beatriz Ferreira, R. silva, João Paulo Costeira, Francisco Melo, M. Veloso, Personalized Assistance for Dressing Users, Proc. of ICSR 2015 - International Conference on Social Robotics, Paris, France. LNCS, Vol. 9388, pp. 359-369; doi: 10.1007/978-3-319-25554-5_36, 2015 - PDF
[2] S. Witwicki, J. C. Montoya, João Messias, J. Reis, Jesús Capitán, Francisco Melo, Pedro Lima, Matthijs Spaan, A Testbed for Autonomous Robot Surveillance (Demonstration), Proc. of AAMAS 2014 - 13th International Conference on Autonomous Agents and Multiagent Systems, pp. 1635-1636, Paris, France, 2014 - PDF
[3] Manuel Lopes, Active Learning for Reward Estimation in Inverse Reinforcement Learning, Proc. of ECML/PKDD 2009 - European Conference on Machine Learning, Bled, Slovenia, 2009 - PDF
[4] B. Kenward, A computational model for social learning mechanisms, Proc. of IROS 2008 - Workshop From motor to interaction learning in robots, Nice, France, 2008
[5] S. P. Meyn, An analysis of reinforcement learning with function approximation, Proc. of ICML 2008 - International Conference on Machine Learning, Helsinki, CA, Finland, 2008 - PDF
[6] Manuel Lopes, Fitted natural actor-critic: A new algorithm for continuous state-action MDPs, Proc. of ECML PKDD 2008 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Antwerp, Belgium, 2008 - PDF
[7] Francisco Melo, Emerging coordination in infinite team Markov games, Proc. of AAMAS 2008 - 7th International Joint Conference on Autonomous Agents and Multi-Agent Systems, Estoril, Portugal, 2008 - PDF
[8] Francisco Melo, Reinforcement learning with function approximation for cooperative navigation tasks, Proc. of the ICRA 2008 - IEEE International Conference on Robotics and Automation, Pasadena, CA, USA, pp. 3321-3327, 2008 - PDF
[9] Francisco Melo, Interaction-Driven Markov Games for Decentralized Multiagent Planning under Uncertainty, Proc. of AAMAS 2008 - the 7th International Conference on Autonomous Agents and Multiagent Systems, Estoril, Portugal, 2008 - PDF
[10] Manuel Lopes, Machine learning for developmental robotics, Proc. of NIPS 2007 - The 21st Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 2007
[11] Francisco Melo, Policy gradient approach to multi-robot, Proc. of NIPS 2007 - The 21st Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 2007
[12] Francisco Melo, Manuel Lopes, Convergence of Independent Adaptive Learners, Proc. of EPIA 2007 - 13th Portuguese Conference on Artificial Intelligence, Guimaraes, Portugal, 2007 - PDF
[13] Francisco Melo, Q-Learning and Function Approximation, Proc. of COLT2007 - 20th Annual Conference on Learning Theory, San Diego, California, USA, 2007 - PDF
[14] Francisco Melo, Learning to Coordinate in Topological Navigation Tasks, Proc. of IAV2007 - 6th IFAC Symposium on Intelligent Autonomous Vehicles, Toulouse, France, 2007 - PDF
[15] Manuel Lopes, Affordance-based imitation learning in robots, Proc. of IROS 2007 - IEEE/RSJ International Conference on Intelligent Robots and Systems, San Diego, California, USA, 2007
[16] Francisco Melo, A POMDP approach to cooperative localization in sparse environments, Proc. of RobotMat2007 - Workshop on Robotics and Mathematics, Coimbra, Portugal, 2007 - PDF
[17] Francisco Melo, Convergence of Q-learning with linear function approximation, Proc. of ECC2007 - European Control Conference, Kos International Convention Centre, Kos, Greece, pp.2671-2678, 2007 - PDF
[18] Manuel Lopes, Unified framework for imitation-like behaviors, Proc. of AISB2007 - 4th International Symposium on Imitation in Animals and Artifacts, pp. 241-250, Newcastle University, Newcastle upon Tyne, United Kingdom, 2007 - PDF
[19] M. Veloso, MODEN: Multi-Robot, Obstacle-Driven Elastic Network Path Planning, Proc. ROBOTICA 2007 - 7th Portuguese Conference on Mobile Robots and Competitions, Paderne, Algarve, Portugal, 2007 - PDF
[20] Francisco Melo, Transition Entropy in Partially Observable Markov Decision Processes, Proc. IAS9 - 9th Intelligent Autonomous Systems, Tokyo, Japan, 2006 - PDF
[21] Francisco Melo, Isabel Ribeiro, Pedro Lima, Navigation Controllability of a Mobile Robot Population, Proc. RoboCup 2004 Symposium, Lisbon, Portugal, 2004 - PDF
[22] Francisco Melo, Pedro Lima, Isabel Ribeiro, Event-driven Modelling and Control of a Mobile Robot Population, Proc. IAS8 - 8th Conference on Intelligent Autonomous Systems, Amsterdam, The Netherlands. pp. 237-244, 2004 - PDF
[1] Francisco Melo, Reinforcement Learning in Cooperative Navigation Tasks, Ph.D. Thesis, Instituto Superior Tecnico, Universidade Tecnica de Lisboa, Portugal, 2007 - PDF
[1] Francisco Melo, Isabel Ribeiro, Q-learning with linear function approximation, Technical Report RT-602-07, Institute for Systems and Robotics, Instituto Superior Tecnico, 2007
[2] Francisco Melo, Manuel Lopes, Convergence of independent adaptive learners, Technical Report RT-603-07, Institute for Systems and Robotics, Instituto Superior Tecnico, 2007
[3] Francisco Melo, Rational and convergent model-free adaptive learning for team Markov games, Technical Report RT-601-07, Institute for Systems and Robotics, Instituto Superior Tecnico, 2007 - PDF
[4] Francisco Melo, Isabel Ribeiro, Convergence of Classical Reinforcement Learning Algorithms and Partial Observability, Technical Report RT-601-06, Institute for Systems and Robotics, Instituto Superior Tecnico, 2006
[5] Francisco Melo, Isabel Ribeiro, Convergence Results for Reinforcement Learning with Partial Observability, Technical Report RT-602-05, Institute for Systems and Robotics, Instituto Superior Tecnico, 2005
[6] Francisco Melo, Isabel Ribeiro, The Use of Transition Entropy in Partially Observable Markov Decision Processes, Technical Report RT-601-05, Instituto for Systems and Robotics, Instituto Superior Tecnico, 2005 - PDF
[7] Alexandre Bernardino, Luís Custódio, João Frazão, Pedro Lima, Francisco Melo, Isabel Ribeiro, José Santos-Victor, Alberto Vale, RESCUE Project Final Report, ISR Technical Report, 2004
[8] Francisco Melo, Isabel Ribeiro, Pedro Lima, Blocking Controllability of a Mobile Robot Population, Relatorio Tecnico, RT-601-04, Instituto de Sistemas e Robotica, Polo do Instituto Superior Tecnico, 2004 - PDF

In the same group

Carlos Azevedo
Meysam Basiri
Carlos Bispo
Oscar Lima
José Corujeira
Luís Custódio
Monica Ekal
Kagan Erunsal
Isabel Ferreira
João Gonçalves
Guilherme Lawless
Pedro Lima
Rute Luz
Lotfi Massarweh
André Mateus
João Pereira
Enrico Piazza
Lashmi Prasad
Eloy Retamino
Isabel Ribeiro
João Sequeira
Porfírio Silva
Tiago Veiga
Rodrigo Ventura
Alicja Wasik