Document Actions
Alessandro Lazaric
 |
Alessandro Lazaric Post-doc INRIA Lille, Team SequeL Parc scientifique de la Haute-Borne, 40 avenue Halley, 59650 Villeneuve d'Ascq, FRANCE email: alessandro.lazaric (at) inria (dot) fr |
- Here are the slides from the tutorial on "Transfer Learning in Reinforcement Learning Domains": part1.pdf part2a.pdf part2b.pdf part3.pdf
- I will give a tutorial with Matthew Taylor on transfer learning in RL at AAMAS-09
- I am in the organization committee of the "On-line Learning with Limited Feedback" workshop at ICML-09
My research activity is mainly focused on Reinforcement Learning (RL) and On-line Learning. During my PhD I studied many topics, from function approximation to exploration and I tried to apply RL to different robotic applications both in simulation and with real robots. At the same time, I investigated what happens when RL techniques are applied to multiagent systems both in cooperative and competitive settings. My PhD thesis focused on the problem of transfer of knowledge in RL. As a post-doc at INRIA I'm working on on-line learning and multi-task learning.
2009
A. Bonarini, A. Lazaric, F. Montrone, and M. Restelli. Reinforcement Distribution in Fuzzy Q-Learning. Fuzzy Sets and Systems, 2008. To appear.2008
E. Ferrante, A. Lazaric, and M. Restelli. Transfer of Task Representation in Reinforcement Learning using Policy-based Proto-value Functions. In Proceedings of the International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 2008.A. Lazaric, E. Munoz de Cote, F. Dercole, and M. Restelli. Bifurcation Analysis of Reinforcement Learning Agents. In Z. Guessoum, K. Tuyls, A. Nowe and D. Kudenko, editors, Adaptive Agents and Multi-Agent Systems III, Lecture Notes in Artificial Intelligence, pp. 129-144, Springer-Verlag, Berlin, Germany, 2008.
A. Lazaric, M. Quaresimale, and M. Restelli. On the Usefulness of Opponent Modeling: the Kuhn Poker case study. In Proceedings of the International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 2008.
A. Lazaric, M. Restelli, and A. Bonarini. Transfer of samples in batch reinforcement learning. In Proceedings of the 25th Annual International Conference on Machine Learning (ICML 2008), pp. 544-551, Omnipress, 2008.
A. Lazaric, M. Restelli, and A. Bonarini. Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods. In Advances in Neural Information Processing Systems 20, pp. 833-840, MIT Press, Cambridge, MA, 2008.
2007
A. Bonarini, A. Lazaric, and M. Restelli. Reinforcement Learning in Complex Environments Through Multiple Adaptive Partitions. In Proceedings of the 10th Congress of the Italian Association for Artificial Intelligence (AI*IA), pp. 531-542, 2007.A. Bonarini, A. Lazaric, and M. Restelli. Piecewise Constant Reinforcement Learning for Robotic Applications. In Proceedings of the 4th International Conference on Informatics in Control, Automation and Robotics (ICINCO), pp. 214-221, 2007.
E. Munoz de Cote, A. Lazaric, M. Restelli, and A. Bonarini. A Learning Approach to Dynamic Coalition Formation. In Proceedings of the AAMAS Workshop on Adaptive and Learning Agents (ALAg), Honolulu, Hawai'i, USA, 2007.
A. Lazaric. Randomized Response-Adaptive Design for Clinical Trials. Technical Report 2007.4, Department of Electronics and Information, Politecnico di Milano, 2007.
A. Lazaric, E. Munoz de Cote, F. Dercole, and M. Restelli. Bifurcation Analysis of Reinforcement Learning Agents. In Proceedings of the Seventh European Symposium on Adaptive and Learning Agents and Multi-Agent Systems, pp. 111-125, MICC Technical Report Series, Maastricht, The Netherlands, April 2007. ISSN 0922--8721
A. Lazaric, E. Munoz de Cote, N. Gatti, and M. Restelli. Reinforcement Learning in Extensive Form Games with Incomplete Information: the Bargaining Case Study. In Proceedings of the International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS), pp. 216-218, Honolulu, USA, May 14-18 2007.
2006
A. Bonarini, A. Lazaric, and M. Restelli. Incremental Skill Acquisition for Self-motivated Learning Animats. In Proceedings of the 9th International Conference on Simulation of Adaptive Behavior (SAB'06), Lecture Notes in Artificial Intelligence, pp. 357-368, Springer Verlag, Berlin, 2006.A. Bonarini, A. Lazaric, and M. Restelli. Learning Reusable Skills through Self-Motivation. In Proceedings of the ICML Workshop on Structural Knowledge Transfer for Machine Learning,
A. Bonarini, A. Lazaric, and M. Restelli. Learning in Complex Environments through Multiple Adaptive Partitions. In Proceedings of the ECAI Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds, 2006.
A. Bonarini, A. Lazaric, and M. Restelli. Self-Development Framework for Reinforcement Learning Agents. In Proceedings of the 5th International Conference on Development and Learning (ICDL), 2006.
E. Munoz de Cote, A. Lazaric, and M. Restelli. Learning to cooperate in multi-agent social dilemmas. In Proceedings of the International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS), pp. 783-785, 2006.
2005
A. Bonarini, A. Lazaric, E. Munoz de Cote, and M. Restelli. Improving Cooperation among Self-Interested Reinforcement Learning Agents. In Proceedings of the ECML Workshop on Reinforcement Learning in Non-Stationary Environments, 2005.A. Bonarini, A. Lazaric, and M. Restelli. LEAP: Learning Entities Adaptive Partitioning. In Proceedings of the NIPS Workshop on Reinforcement Learning Benchmarks and Bake-offs II, 2005.
A. Bonarini, A. Lazaric, and M. Restelli. Learning Optimal Policies using Bound Estimation. Technical Report Department of Electronics and Information, Politecnico di Milano, 2005.
A. Bonarini, A. Lazaric, and M. Restelli. Learning Optimal Policies with State Aggregation. In Proceedings of the 7th European Workshop on Reinforcement Learning (EWRL), 2005.
A. Bonarini, A. Lazaric, and M. Restelli. Yahtzee: a Large Stochastic Environment for RL Benchmarks. In Proceedings of the NIPS Workshop on Reinforcement Learning Benchmarks and Bake-offs II, 2005.
Alessandro Lazaric was born in Milan, Italy, on August 22, 1980. He graduated in 2004 in Informatics Engineering at Politecnico di Milano with full marks (cum laude) and he received a Master of Science at College of Engineering at University of Illinois at Chicago (UIC) in 2005. He received his doctorate from Department of Electronics and Informatics of Politecnico di Milano in April 2008. Since September 2008 he's a post-doc at INRIA (Team SequeL). His main research topics are in in transfer learning, reinforcement learning, on-line learning, and multiagent learning. You can find my cv here (updated: ...)