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 |
News
- 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
Research Interests
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.Publications
Alessandro Lazaric & Remi Munos. "Hybrid Stochastic-Adversarial On-line Learning". Proceedings of the Twenty-Second Annual Conference on Learning Theory (COLT-2009), Montreal, Canada, June 2009. [pdf]2009
Andrea Bonarini, Alessandro Lazaric, Francesco Montrone, & Marcello Restelli. "Reinforcement distribution in fuzzy q-learning". Fuzzy Sets and Systems, 160(10):1420--1443, 2009. [pdf]
Nicola Gatti, Alessandro Lazaric, & Marcello Restelli. "Towards automated bargaining in electronic markets: a partially two-sided competition model". Agent-Mediated Electronic Commerce X and Trading Agent Competition VI, Lecture Notes in Computer Science. Springer, Berlin, Germany, 2009.[pdf]
Alessandro Lazaric, Enrique Munoz de Cote, F. Dercole, & M. Restelli. "Bifurcation analysis of reinforcement learning agents". Adaptive Agents and Multi-Agent Systems III, volume 4865 of Lecture Notes in Artificial Intelligence, pp. 129--144. Springer-Verlag, Berlin, Germany, 2008.[pdf]2008
Alessandro Lazaric, Marcello Restelli, & Andrea Bonarini. "Transfer of samples in batch reinforcement learning". Proceedings of the Twenty-Fifth Annual International Conference on Machine Learning (ICML-2008), pp. 544--551, Helsinki, Finland, July 2008.[pdf]
Eliseo Ferrante, Alessandro Lazaric, & Marcello Restelli. "Transfer of task representation in reinforcement learning using policy-based proto-value functions". Proceedings of the Seventh International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-2008), Estoril, Portugal, May 2008.[pdf]
Alessandro Lazaric, Mario Quaresimale, & Marcello Restelli. "On the usefulness of opponent modeling: the kuhn poker case study". Proceedings of the Seventh International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-2008), Estoril, Portugal, May 2008.[pdf]
Andrea Bonarini, Claudio Caccia, Alessandro Lazaric, & Marcello Restelli. "Batch reinforcement learning for controlling a mobile wheeled pendulum robot". Proceedings of IFIP International Conference on Artificial Intelligence (IFIP-AI-2008), pp. 151--160, Milan, Italy, September 2008.
Alessandro Lazaric. "Knowledge Transfer in Reinforcement Learning". Doctoral thesis. Politecnico di Milano, 2008.[pdf]
Alessandro Lazaric, Marcello Restelli, & Andrea Bonarini. "Reinforcement learning in continuous action spaces through sequential monte carlo methods". Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS-2007), pp. 833--840, Vancouver, Canada, December 2007.[pdf][pdf-appendix]2007
Alessandro Lazaric, Enrique Munoz de Cote, Nicola Gatti, & Marcello Restelli. "Reinforcement learning in extensive form games with incomplete information: the bargaining case study". Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS-2007), Honolulu, Hawai'i, May 2007.[pdf]
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Piecewise constant reinforcement learning for robotic applications". Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics (ICINCO), pp. 214--221, Angers, France, May 2007.
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Reinforcement learning in complex environments through multiple adaptive partitions". Proceedings of the Tenth Congress of the Italian Association for Artificial Intelligence (AI*IA-07), pp. 531--542, Rome, Italy, September 2007.[pdf]
Enrique Munoz de Cote, Alessandro Lazaric, Marcello Restelli, & Andrea Bonarini. "A learning approach to dynamic coalition formation". Proceedings of the AAMAS Workshop on Adaptive and Learning Agents (ALAg-07), Honolulu, Hawa'i, May 2007.[pdf]
Alessandro Lazaric. "Randomized response-adaptive design for clinical trials". Technical Report 2007.4, Department of Electronics and Information, Politecnico di Milano, 2007.
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Incremental skill acquisition for self-motivated learning animats". Proceedings of the Ninth International Conference on Simulation of Adaptive Behavior (SAB-06), volume 4095 of Lecture Notes in Artificial Intelligence, pp. 357--368. Springer Verlag, Berlin, 2006.[pdf]2006
Enrique Munoz de Cote, Alessandro Lazaric, & Marcello Restelli. "Learning to cooperate in multi-agent social dilemmas". Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS-2006), Hakodate, Japan, May 2006.[pdf]
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Self-development framework for reinforcement learning agents". Proceedings of the Fifth International Conference on Development and Learning (ICDL-06), Bloomington, USA, June 2006.
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Learning in complex environments through multiple adaptive partitions". Proceedings of the ECAI Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds, Riva del Garda, Italy, 2006.[pdf]
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Learning reusable skills through self-motivation". Proceedings of the ICML Workshop on Structural Knowledge Transfer for Machine Learning, Pittsburgh, USA, June 2006.[pdf]
Andrea Bonarini, Alessandro Lazaric, Enrique Munoz de Cote, & Marcello Restelli. "Improving cooperation among self-interested reinforcement learning agents". Proceedings of the ECML Workshop on Reinforcement Learning in Non-Stationary Environments, Porto, Portugal, October 2005.[pdf]2005
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Leap: Learning entities adaptive partitioning". Proceedings of the NIPS Workshop on Reinforcement Learning Benchmarks and Bake-offs II, Vancouver, Canada, December 2005.[pdf]
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Yahtzee: a large stochastic environment for RL benchmarks". Proceedings of the NIPS Workshop on Reinforcement Learning Benchmarks and Bake-offs II, Vancouver, Canada, December 2005.[pdf]
Andrea Bonarini, Alessandro Lazaric, & Marcello Restelli. "Learning optimal policies with state aggregation". Proceedings of the Seventh European Workshop on Reinforcement Learning (EWRL), Naples, Italy, October 2005.
Alessandro Lazaric. "Learning wiht Multiple State Aggregation Representations". Master thesis. Department of Computer Science, University of Illinois at Chicago, 2005.
Alessandro Lazaric. "A Multi-Resolution Reinforcement Learning Approach to the Efficient Solution of Complex Problems". Master thesis. Department of Electronics and Information, Politecnico di Milano, 2004.
"Learning with stochastic inputs and adversarial labels" with Remi Munos.Papers in preparation
"Transfer from Multiple Transformed Source Tasks in Batch Reinforcement Learning" with Marcello Restelli, & Andrea Bonarini.
"SMILe: Self-Motivated Incremental Learning" with Marcello Restelli, & Andrea Bonarini.