B
Bruno da Silva
Researcher at University of Massachusetts Amherst
Publications - 82
Citations - 1476
Bruno da Silva is an academic researcher from University of Massachusetts Amherst. The author has contributed to research in topics: Reinforcement learning & Microphone. The author has an hindex of 18, co-authored 79 publications receiving 1193 citations. Previous affiliations of Bruno da Silva include Hogeschool-Universiteit Brussel & Universidade Federal do Rio Grande do Sul.
Papers
More filters
Posted Content
Learning Parameterized Skills
TL;DR: In this paper, the authors introduce a method for constructing skills capable of solving tasks drawn from a distribution of parameterized reinforcement learning problems, using the corresponding learned policies to estimate the topology of the lower-dimensional piecewise-smooth manifold on which the skill policies lie.
Proceedings ArticleDOI
Dealing with non-stationary environments using context detection
TL;DR: It is shown that RL-CD performs better than two standard reinforcement learning algorithms and that it has advantages over methods specifically designed to cope with non-stationarity.
Journal ArticleDOI
Preventing undesirable behavior of intelligent machines.
TL;DR: A general framework for algorithm design is introduced in which the burden of avoiding undesirable behavior is shifted from the user to the designer of the algorithm, and this framework simplifies the problem of specifying and regulating undesirable behavior.
Journal ArticleDOI
Learning in groups of traffic signals
TL;DR: This paper investigates the task of multiagent reinforcement learning for control of traffic signals in two situations: agents act individually and agents can be ''tutored'', meaning that another agent with a broader sight will recommend a joint action.
Journal ArticleDOI
SoundCompass: A Distributed MEMS Microphone Array-Based Sensor for Sound Source Localization
Jelmer Tiete,Federico Dominguez,Bruno da Silva,Laurent Segers,Kris Steenhaut,Abdellah Touhafi +5 more
TL;DR: ThesoundCompass’s hardware and firmware design together with a data fusion technique that exploits the sensing capabilities of the SoundCompass in a wireless sensor network to localize noise pollution sources is presented.