Marcello Restelli's Homepage

Publications Grouped by Category

Journals - Books - Intl_Conf - Natl_Conf - Tech_Rep

Academic Journals [top]
[1] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Leap: an adaptive multi-resolution reinforcement learning algorithm. Journal of Machine Learning Research, 2007. conditionally accepted. [ bib ]
[2] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Reinforcement distribution in fuzzy q-learning. Fuzzy Sets and Systems, 2007. In press. [ bib ]
[3] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Problems and solutions for anchoring in multi-robot applications. Journal of Intelligent and Fuzzy Systems, 2007. In press. [ bib ]
[4] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Learning Fuzzy Classifier Systems: Architecture and Exploration Issues. International Journal on Artificial Intelligence Tools, 16(2):269-289, 2007. [ bib ]
[5] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Concepts and fuzzy models for behavior-based robotics. International Journal of Approximate Reasoning (IJAR), 41(2):110-127, 2006. [ bib ]
International Books [top]
[1] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Mrt: Robotics off-the-shelf with the modular robotic toolkit. In Davide Brugali, editor, Software Engineering for Experimental Robotics, volume 30 of Springer Tracs on Advanced Robotics (STAR). Springer Verlag, Berlin, D, 2007. [ bib ]
[2] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Incremental skill acquisition for self-motivated learning animats. In S. Nolfi, G. Baldassare, R. Calabretta, J. Hallam, D. Marocco, O. Miglino, J. Meyer, and D. Parisi, editors, From Animals to Animats 9. 9th International Conference on Simulation of Adaptive Behavior (SAB'06), Rome, Italy, September 2006, volume 4095 of Lecture Notes in Artificial Intelligence, pages 357-368. Springer Verlag, Berlin, D, 2006. [ bib ]
[3] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Concepts and fuzzy models for behavior-based robotics. In V. Di Ges, F. Masulli, and A. Petrosino, editors, Fuzzy Logic and Applications, volume 2955 of Lecture Notes in Artificial Intelligence, pages 72-79. Springer Verlag, Berlin, D, 2006. [ bib ]
[4] Andrea Bonarini, Francesco Montrone, and Marcello Restelli. Reinforcement distribution in continuous state action space fuzzy q-learning: a novel approach. In I. Bloch, A. Petrosino, and G.B. Tettamanzi, editors, Fuzzy Logic and Applications. 6th International Workshop, WILF 2005, Crema, Italy, September 15-17, 2005, Revised Selected Papers, volume 3849 of Lecture Notes in Artificial Intelligence, pages 40-45. Springer Verlag, Berlin, D, 2006. [ bib ]
[5] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Filling the gap among coordination, planning, and reaction using a fuzzy cognitive model. In D. Polani, B. Browning, A. Bonarini, and K. Yoshida, editors, RoboCup 2003: Robot Soccer World Cup VII, volume 3020 of Lecture Notes in Artificial Intelligence, pages 662-669. Springer Verlag, Berlin, D, 2004. [ bib ]
[6] Andrea Bonarini, Matteo Matteucci, Marcello Restelli, and Domenico G. Sorrenti. Milan robocup team 2003. In D. Polani, B. Browning, A. Bonarini, and K. Yoshida, editors, RoboCup 2003: Robot Soccer World Cup VII, volume 3020 of Lecture Notes in Artificial Intelligence, page on CD. Springer Verlag, Berlin, D, 2004. [ bib ]
[7] Marcello Restelli, Domenico G. Sorrenti, and Fabio M. Marchese. A probabilistic framework for weighting different sensor data in murea. In D. Polani, B. Browning, A. Bonarini, and K. Yoshida, editors, RoboCup 2003: Robot Soccer World Cup VII, volume 3020 of Lecture Notes in Artificial Intelligence, pages 678-685. Springer Verlag, Berlin, D, 2004. [ bib ]
[8] M. Restelli, D. G. Sorrenti, and F. M. Marchese. Murea: A multi-resolution evidence accumulation method for robot localization in known environments. In G. A. Kaminka, P. U. Lima, and R. Rojas, editors, RoboCup 2002: Robot Soccer World Cup VI, volume 2752 of Lecture Notes in Artificial Intelligence, pages 351-358. Springer Verlag, Berlin, D, 2003. [ bib ]
[9] Andrea Bonarini, Giovanni Invernizzi, Fabio M. Marchese, Matteo Matteucci, Marcello Restelli, and Domenico G. Sorrenti. Fun2mas: The milan robocup team. In A. Birk, S. Coradeschi, and S. Tadokoro, editors, RoboCup 2001: Robot Soccer World Cup V, volume 2377 of Lecture Notes in Artificial Intelligence, pages 639-642. Springer Verlag, Berlin, D, 2002. [ bib ]
[10] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. A framework for robust sensing in multi-agent systems. In A. Birk, S. Coradeschi, and S. Tadokoro, editors, RoboCup 2001: Robot Soccer World Cup V, volume 2377 of Lecture Notes in Artificial Intelligence, pages 287-292. Springer Verlag, Berlin, D, 2002. [ bib ]
[11] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Concepts for anchoring in robotics. In F. Esposito, editor, AI*IA 2001: Advances in Artificial Intelligence, volume 2175 of Lecture Notes in Computer Science, pages 327-332. Springer Verlag, Berlin, D, 2001. [ bib ]
Proceedings of International Conferences [top]
[1] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Piecewise constant reinforcement learning for robotic applications. In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics (ICINCO 2007), 2007. to appear. [ bib ]
[2] Alessandro Lazaric, Enrique Munoz de Cote, Nicola Gatti, and Marcello Restelli. Reinforcement learning in extensive form games with incomplete information: the bargaining case study. In Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS 2007), 2007. to appear. [ bib ]
[3] Alessandro Lazaric, Enrique Munoz de Cote, Marcello Restelli, and Andrea Bonarini. A learning approach to dynamic coalition formation. In Proceedings of the AAMAS 2007 workshop on “Adaptive and Learning Agents”, 2007. to appear. [ bib ]
[4] Alessandro Lazaric, Enrique Munoz de Cote, Fabio Dercole, and Marcello Restelli. Bifurcation analysis of reinforcement learning agents in the selten's horse game. In K. Tuyls, S. De Jong, M. Ponsen, and K. Veerbeeck, editors, Proceedings of the Symposium on “Adaptive Learning Agents and Multi-Agent Systems” (ALAMAS 2007), pages 111-125, April 2007. [ bib ]
[5] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Learning in complex environments through multiple adaptive partitions. In Proceedings of the ECAI'06 workshop on “Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds”, pages 7-12, August 2006. [ bib ]
[6] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Learning reusable skills through self-motivation. In Proceedings of the ICML'06 workshop on “Structural Knowledge Transfer for Machine Learning”, June 2006. [ bib ]
[7] Andrea Bonarini, Alessandro Lazaric, Marcello Restelli, and Patrick Vitali. Self-development framework for reinforcement learning agents. In Proceedings of the Fifth International Conference on Development and Learning (ICDL 2006), page on CD, June 2006. [ bib ]
[8] Andrea Bonarini, Alessandro Lazaric, Jose Enrique Munoz de Cote, and Marcello Restelli. Learning to cooperate in multi-agent repeated games. In Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS 2006), pages 783-785, May 2006. [ bib ]
[9] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Leap: Learning entities adaptive partitioning. In Proceedings of NIPS 2005 Workshop on Reinforcement Learning Benchmarks and Bake-offs II, December 2005. [ bib ]
[10] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Yahtzee: a large stochastic environment for rl benchmarks. In Proceedings of NIPS 2005 Workshop on Reinforcement Learning Benchmarks and Bake-offs II, December 2005. [ bib ]
[11] Andrea Bonarini, Alessandro Lazaric, Jose Enrique Munoz de Cote, and Marcello Restelli. Improving cooperation among self-interested reinforcement learning agents. In Proceedings of ECML'05 workshop on Reinforcement Learning in Non-Stationary Environments, pages 25-36, October 2005. [ bib ]
[12] Andrea Bonarini, Alessandro Lazaric, and Marcello Restelli. Learning optimal policies with state aggregation. In Proceedings of European Workshop on Reinforcement Learning (EWRL-8), October 2005. [ bib ]
[13] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Automatic error detection and reduction for an odometric sensor based on two optical mice. In Proceedings of International Conference on Robotics and Automation (ICRA'05), pages 1687-1692, April 2005. [ bib ]
[14] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. A kinematic-independent dead-reckoning sensor for indoor mobile robotics. In Proceedings of the 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'04), page on CD, October 2004. [ bib ]
[15] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Dead reckoning for mobile robots using two optical mice. In Proceedings of the 1st IEEE International Conference in Control, Automation and Robotics (ICINCO'04), volume 2, pages 87-94, August 2004. [ bib ]
[16] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. A model to manage data reliability in behavior-based robotics. In Proceedings of IAV 2004, 5th IFAC Symposium on Intelligent Autonomous Vehicles (IAV'04), page on CD, July 2004. [ bib ]
[17] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. A novel model to rule behavior interaction. In Proceedings of the 8th Conference on Intelligent Autonomous Systems (IAS-8), pages 199-206, 2004. [ bib ]
[18] Andrea Bonarini and Marcello Restelli. An architecture to implement adaptive cooperative strategies for heterogeneous agents. In Proceedings of the Workshop on Cooperative Robotics in the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'02), October 2002. [ bib ]
[19] Andrea Bonarini and Marcello Restelli. An architecture to implement agents co-operating in dynamic environments. In Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS 2002), pages 1143-1144, July 2002. [ bib ]
[20] M. Restelli, D. G. Sorrenti, and F. M. Marchese. A robot localization method based on evidence accumulation and multi-resolution. In Proceedings of the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'02), pages 415-420, 2002. [ bib ]
[21] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Anchoring: do we need new solutions to an old problem or do we have old solutions for a new problem? In Proceedings of the AAAI Fall Symposium on “Anchoring Symbols to Sensor Data in Single and Multiple Robot Systems”, pages 79-86, November 2001. [ bib ]
Proceedings of National Conferences [top]
[1] Marcello Restelli, Davide Lonoce, Maurizio Villa, and Andrea Bonarini. Hierarchical cooperative learning for multi-agent heterogeneous systems. In Conferenza Italiana sui Sistemi Intelligenti (CISI-04), page on CD, September 2004. [ bib ]
[2] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Concepts and fuzzy models for control and coordination in robotics. In Proceedings of the Congress of the Italian Association for Industrial Robotics (SIRI-2003), page on CD, July 2003. [ bib ]
[3] Marcello Restelli, Domenico G. Sorrenti, and Fabio M. Marchese. Evidence accumulation method for mobile robot localization. In Proceedings of AI*IA 2002 Workshop su agenti robotici, page on CD, September 2002. [ bib ]
[4] Andrea Bonarini and Marcello Restelli. An architecture for adaptive coordination of heterogeneous agents. In Proceedings of AI*IA 2002 Workshop su agenti robotici, page on CD, September 2002. [ bib ]
Technical Reports [top]
[1] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. Learning optimal policies using bound estimation. Technical Report N 2005.22, Politecnico di Milano, 2005. [ bib ]
[2] Andrea Bonarini, Matteo Matteucci, and Marcello Restelli. A novel model to rule behavior interaction. Technical Report 2003.44, Politecnico di Milano, 2003. [ bib ]
[3] Marcello Restelli. Murea: A multi-resolution evidence accumulation method for robot localization in known environments. Technical Report 2002.37, Politecnico di Milano, 2002. [ bib ]