Peter Vrancx

I am a post-doc assistant for the Department of Computer Science and researcher at the Computational Modeling Lab.

• "Grondslagen van de Informatica 2"
• "Multi-Agent Learning"
• "Multi-Agent Learning Seminar"
• "Techniques of AI"
• "Machine Learning"
• "Integrated Project 3rd Bachelor"

Research interests: Machine Learning, Robotics, Reinforcement Learning, Multi-Agent Reinforcement learning & Game Theory.

Research Links:

• The Adaptive and Learning Agents workshop 2012
• IJCNN 2012 Special Session on Real World Applications of Reinforcement Learning
• The Adaptive and Learning Agents workshop 2011
• Robotics projects

Books

[2012, book | www | bibTeX]

Adaptive and Learning Agents, Vrancx, P., Knudson, M., and Grzes, M., Eds., Berlin, Germany: Springer, 2012.

[2012, book | www | bibTeX]

Proceedings of the 12th Adaptive and Learning Agents Workshop, Howley, E., Vrancx, P., and Knudson, M., Eds., Valencia,Spain: AAMAS2012, 2012.

[2011, book | www | bibTeX]

Proceedings of the 11th Adaptive and Learning Agents Workshop, Vrancx, P., Knudson, M., and Grzes, M., Eds., Taipei,Taiwan: AAMAS11, 2011.

[2010, book | www | bibTeX]

P. Vrancx, Decentralised Reinforcement Learning in Markov Games, Brussels,Belgium: ASP-VubPress, 2010.

Book Chapters

[2012, inbook | www | bibTeX]

A. Nowé, P. Vrancx, and Y.-M. De Hauwere, "Reinforcement Learning: State-of-the-Art," , Wiering, M. and van Otterlo, M., Eds., Springer, 2012, pp. 441-470.

[2010, inbook | www | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Multi-agent systems and large state spaces," , Hakensson, A., Hartung, R., and Nguyen, N. T., Eds., Springer, 2010, pp. 181-205.

[2008, incollection | www | bibTeX]

K. Verbeeck, A. Nowé, P. Vrancx, and M. Peeters, "Multi-Automata Learning," , Weber, C., Elshaw, M., and Mayer, N. M., Eds., I-Tech Education and Publishing, 2008, pp. 167-185.

Phd Thesis

[2010, phdthesis | vrancxphd.pdf | bibTeX]

P. Vrancx, "Decentralised Reinforcement Learning in Markov Games," PhD Thesis , Brussels, Belgium, 2010.

Journals and Lecture Notes

[2010, article | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Generalized Learning Automata for Multi-agent Reinforcement Learning," Journal of AI Communications: Special issue, 2010.

[2010, article | www | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Analyzing the Dynamics of Stigmergetic Interactions through Pheromone Games," Theoretical Computer Science. Special Issue on Swarm Intelligence: Theory, pp. 2116-2126, 2010.

[2008, article | www | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowe, "Decentralized Learning in Markov Games," IEEE Transactions on Systems, Man and Cybernetics (Part B: Cybernetics), vol. 38, iss. 4, pp. 976-81, 2008.

[2008, article | vrancxalamas07.pdf | www | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Networks of learning automata and limiting games," Lecture Notes in Artificial Intelligence, ALAMAS III, vol. 4865, pp. 224-238, 2008.

[2007, article | vrancxkes2007.pdf | www | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Optimal Convergence in Multi-Agent MDPs," Lecture Notes in Computer Science, Knowledge-Based Intelligent Information and Engineering Systems (KES 2007), vol. 4694, pp. 107-114, 2007.

[2007, article | vrancxkdecb06.pdf | www | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Analyzing Stigmergetic Algorithms Through Automata Games," Lecture Notes in BioInformatics, Knowledge Discovery and Emergent Complexity in Bioinformatics, vol. 4366, pp. 145-156, 2007.

[2006, article | www | bibTeX]

P. Vrancx, A. Nowé, and K. Steenhaut, "Multi-type ACO for Light Path Protection," Lecture Notes in Computer Science, Learning and Adaption in Multi-Agent Systems, vol. 3898, pp. 207-215, 2006.

[2006, article | www | bibTeX]

P. Vrancx and A. Nowe, "Using Pheromone Repulsion to Find Disjoint Paths (Extended Abstract)," Lecture Notes in Computer Science, ANTS 2006, vol. 4150, pp. 522-524, 2006.

[2004, article | www | bibTeX]

A. Nowé, K. Verbeeck, and P. Vrancx, "Multi-type Ant Colony: The Edge Disjoint Paths Problem," Lecture Notes in Computer Science, ANTS 2004, pp. 202-213, 2004.

Refereed Conference

[2012, conference | bibTeX]

K. Van Vaerenbergh, M. Gagliolo, A. Rodriguez, P. Vrancx, A. Nowe, J. Stoev, S. Goossens, G. Pinte, and W. Symens, "Improving wet clutch engagement with Reinforcement Learning," in Proc. International Joint Conference on Neural Networks (IJCNN 2012), Brisbane, Australia, 2012.

[2012, conference | bibTeX]

A. Rodriguez, P. Vrancx, R. Grau, and A. Nowe, "An RL approach to Common-Interest Continuous Action Games," in Proc. 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012), Valencia, Spain, 2012.

[2011, conference | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Solving Delayed Coordination Problems in MAS (Extended Abstract)," in Proc. the 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS2011), Taipei, Taiwan, 2011.

[2011, conference | bibTeX]

P. Vrancx, Y.-M. De Hauwere, and A. Nowé, "Transfer Learning for Multi-agent Coordination," in Proc. International Conference on Agents and Artificial Intelligence (ICAART 2011), Rome, Italy, 2011.

[2011, conference | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Adaptive State Representations For Multi-agent Reinforcement Learning," in Proc. International Conference on Agents and Artificial Intelligence (ICAART 2011), Rome, Italy, 2011.

[2010, conference | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Taking Turns in General Sum Markov Games," in Proc. 9th International Conference on Agents and Multi-Agent Systems (AAMAS 2010), Toronto, Canada, 2010.

[2010, conference | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Learning Multi-Agent State Space Representations," in Proc. 9th International Conference on Agents and Multi-Agent Systems (AAMAS 2010), Toronto, Canada, 2010.

[2009, conference | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Learning what to observe in Multi-agent Systems," in Proc. The 21st Benelux Conference on Artificial Intelligence, Eindhoven, The Netherlands, 2009.

[2008, conference | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Using Generalized Learning Automata for State Space Aggregation in MAS," in Proc. 12th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, Zagreb, Croatia, 2008.

[2008, conference | vrancxaamas08.pdf | bibTeX]

P. Vrancx, K. Tuyls, R. Westra, and A. Nowé, "Switching Dynamics of Multi-Agent Learning," in Proc. International joint conference on Autonomous Agents and Multi-Agent Systems (AAMAS'08), 2008.

[2008, conference | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Multi-Agent state space aggregation using Generalized Learning Automata (Compressed Contribution)," in Proc. Benelearn, The Annual Belgian-Dutch Machine Learning Conference, Spa, Belgium, 2008.

[2008, conference | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Decentralized Learning in Markov Games (Extended Abstract)," in Proc. 20th Belgian-Dutch Conference on Artificial Intelligence (BNAIC 2008), Enschede, The Netherlands, 2008.

[2007, conference | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Optimal Convergence in Multi-Agent MDPs (Extended Abstract)," in Proc. 19th Belgian-Dutch Conference on Artificial Intelligence (BNAIC 2007), Utrecht, The Netherlands, 2007, pp. 413-414.

[2005, conference | bibTeX]

R. Bello, A. Nowé, Y. Caballero, Y. Gómez, and P. Vrancx, "Using Ant colony System meta-heuristic and Rough Set Theory for Feature Selection," in Proc. 6th Metaheuristics International Conference (MIC2005), Vienna, Austria, 2005.

[2005, conference | www | bibTeX]

R. Bello, A. Nowé, Y. Caballero, Y. Gómez, and P. Vrancx, "A model based on ant colony system and rough set theory for feature selection," in Proc. 2005 conference on Genetic and evolutionary computation, New York, USA, 2005, pp. 275-276.

Refereed Workshop

[2012, inproceedings | bibTeX]

A. Rodriguez, P. Vrancx, R. Grau, and A. Nowe, "A Reinforcement Learning Approach to Coordinate Exploration with Limited Communication in Continuous Action Games," in Proc. AAMAS Workshop on Adaptive and Learning Agents (ALA12), Valencia, Spain, 2012, pp. 17-24.

[2011, inproceedings | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Future Sparse Interactions: A MARL Approach," in Proc. the European Workshop on Reinforcement Learning, Athens, Greece, 2011.

[2011, inproceedings | bibTeX]

P. Gurzi, K. Steenhaut, A. Nowe, and P. Vrancx, "Learning a Pricing Strategy in Multi-Domain DWDM Networks," in Proc. IEEE International Workshop on Local and Metropolitan Area Networks, Chapel Hill, USA, 2011.

[2011, inproceedings | bibTeX]

A. Rodriguez Abed, M. Gagliolo, P. Vrancx, R. Grau, and A. Nowe, "Improving the performance of Continuous Action Reinforcement Learning Automata," in Proc. the European Workshop on Reinforcement Learning, Athens, Greece, 2011.

[2011, inproceedings | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Detecting and Solving Future Multi-Agent Interactions," in Proc. AAMAS Workshop on Adaptive and Learning Agents, Taipei, Taiwan, 2011, pp. 45-52.

[2011, inproceedings | bibTeX]

T. Brys, Y.-M. De Hauwere, A. Nowé, and P. Vrancx, "Local Coordination in Distributed Constraint Optimization Problems," in Proc. The 9th European Workshop on Multi-Agent Systems, Maastricht, The Netherlands, 2011.

[2010, inproceedings | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Taking Turns in General Sum Markov Games," in Proc. Adaptive and Learning Agents Workshop 2010, Toronto, Canada, 2010.

[2009, inproceedings | bibTeX]

Y.-M. De Hauwere, P. Vrancx, and A. Nowé, "Multi-layer learning and knowledge transfer in MAS," in Proc. 7th European Workshop on Multi-Agent Systems (EUMAS), Ayia Napa, Cyprus, 2009.

[2007, inproceedings | verbeeckalamas07.pdf | bibTeX]

K. Verbeeck, P. Vrancx, and A. Nowé, "Networks of learning automata and limiting games," in Proc. Adaptive Learning Agents and Multi-Agent Systems Workshop 2007, Maastricht, The Netherlands, 2007, pp. 171-183.

[2007, inproceedings | vrancxalag07.pdf | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Limiting Games of Multi-agent Multi-state Problems," in Proc. Workshop on Adaptive and Learning Agents 2007, 6th International Conference on Autonomous Agents and Multi-Agents Systems (AAMAS 2007), Hawaii, USA, 2007.

[2005, inproceedings | www | bibTeX]

P. Vrancx, A. Nowé, and K. Steenhaut, "Multi-type ACO for Light Path Protection," in Proc. Learning and Adaptation in MAS workshop (LAMAS), 4th International Conference on Autonomous Agents and Multi-Agents Systems (AAMAS 2005), Utrecht, The Netherlands, 2005.

[2005, inproceedings | bibTeX]

P. Vrancx, A. Nowe, and K. Steenhaut, "Multi-type ACO for Light Path Protection (Extended Abstract)," in Proc. Third European Workshop on Multi-Agent Systems (EUMAS 2005), Brussels, Belgium, 2005, pp. 513-514.

Technical reports

[2008, techreport | vrancxtr092008.pdf | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Analyzing the Dynamics of Stigmergetic Interactions through Pheromone Games," Computational Modeling Lab, Vrije Universiteit Brussel, Brussels, Belgium, COMO/09/2008, 2008.

[2006, techreport | vrancxtr122006.pdf | bibTeX]

P. Vrancx, K. Verbeeck, and A. Nowé, "Decentralized Learning in Markov Games," Computational Modeling Lab, Vrije Universiteit Brussel, Brussels, Belgium, COMO/12/2006, 2006.

[2004, mastersthesis | bibTeX]

P. Vrancx, "Multi-type Ant System: The introduction of competition to Ant algorithms," Master's Dissertation , Brussels, Belgium, 2004.

[2010, unpublished | bibTeX]

Matthew Taylor and Fransisco Melo and Katja Verbeeck and Steven de Jong and Peter Vrancx, AAMAS10 Tutorial: Reinforcement Learning and Beyond, 2010.

[2009, unpublished | www | bibTeX]

Katja Verbeeck and Steven de Jong and Peter Vrancx, AAMAS09 Tutorial: Multi-agent Learning and Learning Automata, 2009.

[2008, unpublished | master.pdf | www | bibTeX]

Ann Nowé and Katja Verbeeck and Peter Vrancx, EWRL08 Tutorial: Multi-Automata Learning, 2008.