CV Lattes
ResearcherID
ORCID
Google Scholar Citations
Universidade de São Paulo (USP). Escola Politécnica (EP) (Institutional affiliation from the last research proposal) Birthplace: Brazil
Anna Helena Reali Costa is a full professor at the Escola Politécnica of the Universidade de São Paulo (EPUSP), Brazil. She holds a PhD in Electrical Engineering from EPUSP, and a master's and a bachelor's degree in Electrical Engineering, both from Centro Universitário FEI, in São Bernardo do Campo, SP. She was a visiting researcher during her PhD, working on computer vision and intelligent mobile robots, at the Institut für Prozessrechentechnik und Robotik (IPR) of the Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany. She completed a postdoctoral fellowship in the integration of planning and learning for intelligent mobile robots at Carnegie Mellon University (CMU), USA. She is the Director of the Center for Data Science (C2D), a partnership between USP and Itaú-Unibanco bank, and a researcher at the Center for Artificial Intelligence (C4AI) at USP, a partnership between USP, IBM and FAPESP. She is an Associate Editor of the journal Engineering Applications of Artificial Intelligence and of Machine Learning and Knowledge Extraction. She is a member of the Special Committee on Artificial Intelligence of the Brazilian Computer Society. Her main interests lie in artificial intelligence, in particular in real-time learning, especially reinforcement learning. (Source: Lattes Curriculum)
| News published in Agência FAPESP Newsletter about the researcher |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |
The "offshore of tomorrow" is being defined in our generation. Awaken by climate change, we were made aware that the exploration of fossil fuels for the sole use of thermal energy cannot be sustainable in the distant future. The effect humanity has played in changing the climate of the planet by the emission of greenhouse gases is a pressing agenda for many, if not all, countries committe…
The program of the 1st. Workshop on Transfer in Reinforcement Learning (TiRL) involves two invited talks, papers presented and discussions on the various topics related to transfer learning (TL) and reinforcement learning (RL). Authors are encouraged to submit to any of the following categories: Research Paper (8 pages in length), in which an original contribution to the field is expected…
Intelligent systems are machines that have their own goals, perceive, respond and learn based on their experiences. Reinforcement Learning (RL) is a powerful tool for this purpose because the system autonomously learns a policy, through trial and error in repeated interactions with the environment. This project seeks to increase the dissemination of the RL technology and advance the front…
This research project aims to scientific understanding, development and use of technologies necessary to provide cognitive agents with significant levels of autonomy, perceptual skills and ability to reason, to learn, to solve problems, to adapt and to make decisions, through appropriate formalisms for representing and using knowledge. The following aspects will be explored for achieving …
(Only some records are available in English at this moment)
Reinforcement Learning is a powerful to train intelligent agents because the learning is performed completely autonomously. This learning is accomplished through repetitive interactions between agents and the environment through trial and error, until agents have enough information to properly actuate in order to solve a given task. However, an agent can take a long time to determine whic…
Transferring the knowledge acquired by a robot in previous experiences to new tasks is one of the challenges faced by the Artificial Intelligence field nowadays. This scientific research project has the objective to propose, develop and evaluate abstraction methods applied to the transfer of policies learned in some tasks by the agent to new, similar and unseen tasks, using the Reinforcem…
The use of omnidirectional images to extract attributes and form object-based maps is an important topic in mobile robotics and computer vision since they allow the capture of the scene around the observer with a wide field of view. However, this advantage comes with the difficulty in processing distorted images. The study of how best to rectify the image obtained and thus be able, for ex…
(Only some records are available in English at this moment)
Reinforcement Learning (RL) is a popular solution to train autonomous agents to solve tasks in environments with unknown dynamics. Despite the recent successes of RL in solving increasingly challenging tasks, it suffers from an excessive requirement of samples of interactions with the environment in order to learn a good solution. When applied to Multiagent Systems (MAS), RL allows to tra…
| 1 / 1 | Ongoing grants |
| 9 / 6 | Completed research grants |
| 10 / 6 | Completed scholarships in Brazil |
| 2 / 1 | Completed scholarships abroad |
| 22 / 14 | All research grants and scholarships |
| Associated processes | |