Experience generalization for multi-agent reinforcement learning

On-line learning methods have been applied successfully in multi-agent systems to achieve coordination among agents. Learning in multi-agent systems implies in a non-stationary scenario perceived by the agents, since the behavior of other agents may change as they simultaneously learn how to improve their actions. Non-stationary scenarios can be modeled as Markov Games, which can be solved using the Minimax-Q algorithm a combination of Q-learning (a Reinforcement Learning (RL) algorithm which directly learns an optimal control policy) and the Minimax algorithm. However, finding optimal control policies using any RL algorithm (Q-learning and Minimax-Q included) can be very time consuming. Trying to improve the learning time of Q-learning, we considered the QS-algorithm. in which a single experience can update more than a single action value by using a spreading function. In this paper, we contribute a Minimax-QS algorithm which combines the Minimax-Q algorithm and the QS-algorithm. We conduct a series of empirical evaluation of the algorithm in a simplified simulator of the soccer domain. We show that even using a very simple domain-dependent spreading function, the performance of the learning algorithm can be improved.

The calcium wave model of the perception-action cycle: Evidence from semantic relevance in memory experiments

We present a general model of brain function (the calcium wave model), distinguishing three processing modes in the perception-action cycle. The model provides an interpretation of the data from experiments on semantic memory conducted by the authors. © 2013 Pereira Jr, Santos and Barros.

PIBID e ensino de línguas estrangeiras: o impacto no projeto Luz, câmera... action!

PIBID's subproject from the Letras course at a public university from the interior of Sao Paulo has, as a vision, the teaching of languages in a different way, where the culture is something to be known, not only mentioned, and, because of that, students feel close to the language learning process, for the language is not something to be learned just as grammar, it is, in fact, to be learned as something more complex than that, making the connection between student and language and its values. The students have, as an objective the knowledge and formation in teaching, by participation in public schools where they could put the theory learned during the Letras course in the university in practice with students that could benefit from learning new languages. The public school, mentioned in this research, offered the opportunity for the PIBID students to participate in a project that already existed in this school, where the students were supposed to produce a script based in a tale, and with the script, they were supposed to produce a short movie and a trailer. In 2014, in the first year of the participation of PIBID in the project, PIBID students were asked to choose a tale in the languages that are currently part of the subproject, for the students could use as a base to the production of the short movie. This project is called Luz, Câmera… Action! and the main objective of this research was to verify the participation of PIBID in the project. For such, it was used a semi-structured open questionnaire, which sought to investigate how students and supervisors from the school understood and analyzed PIBID's participation in the project