Bruno Castro da Silva

Ph.D. Candidate
Autonomous Learning Laboratory
Department of Computer Science
University of Massachusetts Amherst

140 Governors Drive
Amherst, MA 01003-9264 U.S.A.

bsilva at cs dot umass dot edu




I am a graduate student at the Autonomous Learning Laboratory working under the supervision of Andrew Barto. I am interested in the construction of reusable skills in reinforcement learning, and in particular in generalized policies capable of solving a class of tasks drawn from a distribution of parameterized control problems. I am also interested in designing algorithms for efficiently exploring large state spaces.

In the past year I have been collaborating with Prof. Victor Lesser on the problem of designing organizationally adept agents and on coordinating learning through emergent distributed supervisory control.

In the Summer of 2011 I worked with Gianluca Baldassarre at the Laboratory of Computational Embodied Neuroscience, in the Istituto di Scienze e Tecnologie della Cognizione, in Rome, on the problem of learning parameterized skills from data.

In 2007 I completed my Masters Degree in Computer Science under the supervision of Prof. Ana Bazzan at the Universidade Federal do Rio Grande do Sul, Brazil. During my MSc. I worked on algorithms for dealing with non-stationary environments in reinforcement learning problems. I completed my B.S. in Computer Science cum laude at that same university in 2004.

Here is my curriculum vitae.


Some publications

  1. da Silva, B.C.; Konidaris, G.; Barto, A.G. Learning Parameterized Skills. Proceedings of the 29th International Conference on Machine Learning (ICML 2012). Scotland, 2012.

  2. da Silva, B.C.; Barto, A.G. TD-Δπ: A Model-Free Algorithm for Efficient Exploration. Proceedings of the 26th Conference on Artificial Intelligence (AAAI 2012). Canada, 2012.

  3. da Silva, B.C.; Barto, A.G.; Kurose, J. Designing Adaptive Sensing Policies for Meteorological Phenomena via Spectral Analysis of Radar Images. Technical Report UM-CS-2012-006, Department of Computer Science, University of Massachusetts Amherst. USA, 2012.

  4. Bazzan, A.L.C.; Oliveira, D., da Silva, B.C. Learning in Groups of Traffic Lights. Journal of Engineering Applications of Artificial Intelligence. 2010.

  5. da Silva, B.C.; Basso, E.W.; Bazzan, A.L.C.; Engel, P.M. Dealing with Non-Stationary Environments using Context Detection. Proceedings of the 23rd International Conference on Machine Learning (ICML 2006). USA, 2006.

  6. da Silva, B.C.; Basso, E.W.; Bazzan, A.L.C.; Engel, P.M. Improving Reinforcement Learning with Context Detection. Proceedings of the 5th International Joint Conference On Autonomous Agents And Multiagent Systems (AAMAS 2006). Japan, 2006.

  7. da Silva, B.C.; Oliveira, D.; Basso, E.W., Bazzan, A.L.C. Adaptive Traffic Control with Reinforcement Learning. Proceedings of the 4th Workshop on Agents in Traffic and Transportation (ATT 2006). Japan, 2006.

  8. Almeida, L.; da Silva, B.C.; Bazzan, A.L.C. Towards a physiological model of emotions: first steps. Proceedings of the 2004 AAAI Spring Symposium Series. USA, 2004.